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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential danger or threats

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "rangers" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     periodic
    -0.70
    ately
    -0.68
     iron
    -0.64
    balanced
    -0.64
     Hilbert
    -0.63
    bal
    -0.63
     floor
    -0.62
    ¢
    -0.61
     earliest
    -0.60
     instantaneous
    -0.59
    POSITIVE LOGITS
    angers
    1.34
    anger
    0.96
    auga
    0.88
     unlaw
    0.86
    folk
    0.84
     behav
    0.77
     extraord
    0.76
    ocial
    0.73
    keeper
    0.72
    chwitz
    0.69
    Act Density 0.004%

    No Known Activations