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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreement or alignment with a plan or idea

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disagreement or mixed reactions to plans or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emergencies
    -0.72
     cumbers
    -0.63
    llular
    -0.62
    escape
    -0.61
     harvest
    -0.61
    ò
    -0.61
    eworks
    -0.61
     eleph
    -0.61
    tenance
    -0.60
    stall
    -0.59
    POSITIVE LOGITS
     disagree
    0.88
     dismissing
    0.83
     disagrees
    0.82
     recommending
    0.79
     endorsing
    0.79
     disappro
    0.78
     opinion
    0.77
     rejecting
    0.76
    agree
    0.74
     passionately
    0.73
    Act Density 0.773%

    No Known Activations