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

    Neuronpedia

    INDEX
    Explanations

    negative phrases related to barriers or restrictions in transactions

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

    Absence or lack of something

    np_acts-logits-general · gemini-2.0-flash

    eliminating costs or requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.78
     pleaſure
    -0.77
     Majefty
    -0.73
    RenderAtEndOf
    -0.72
     ſtate
    -0.71
     ſeveral
    -0.68
    "]);
    -0.67
     ſon
    -0.66
     ſche
    -0.66
     ſever
    -0.66
    POSITIVE LOGITS
     worry
    0.71
     need
    0.70
     complicated
    0.68
     necesidad
    0.66
     Worry
    0.65
     worrying
    0.64
     hassle
    0.63
    worry
    0.62
     gim
    0.61
     hass
    0.61
    Act Density 0.291%

    No Known Activations