Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to plans and objectives in research and professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "to" and relates to positive actions

    np_acts-logits-general · gemini-2.0-flash

    to + verbs of purpose/action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     messing
    -0.68
     pulled
    -0.67
     ACTUALLY
    -0.65
     shoving
    -0.63
     begged
    -0.63
     davvero
    -0.62
     shoved
    -0.62
     telling
    -0.62
     shove
    -0.62
     REALLY
    -0.61
    POSITIVE LOGITS
     enhance
    1.12
     promote
    1.02
     foster
    0.96
     facilitate
    0.95
     enhancing
    0.93
    Enhance
    0.91
     improve
    0.91
    enhance
    0.91
     promoting
    0.85
     increase
    0.84
    Act Density 0.663%

    No Known Activations