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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manifests
    -0.70
     Lives
    -0.68
     Journey
    -0.64
     Born
    -0.63
     Frag
    -0.62
     Tale
    -0.61
    Frag
    -0.59
     manifestation
    -0.59
    entary
    -0.59
    ancer
    -0.59
    POSITIVE LOGITS
     concede
    1.05
     revise
    0.96
     admit
    0.92
     convince
    0.91
     conclud
    0.90
     announce
    0.89
     insist
    0.88
     realize
    0.87
     relent
    0.87
     apologize
    0.86
    Act Density 0.397%

    No Known Activations