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

    Neuronpedia

    INDEX
    Explanations

    differences between things or situations

    oai_token-act-pair · gpt-3.5-turbo

    comparisons between different subjects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERS
    -0.70
    thora
    -0.67
    ¬¼
    -0.66
    igion
    -0.65
    Ãį
    -0.63
     exting
    -0.62
    Kings
    -0.62
    Eva
    -0.62
    WIND
    -0.61
    ILY
    -0.61
    POSITIVE LOGITS
     nor
    0.76
     wherein
    0.69
    dat
    0.66
     Nor
    0.64
     whereby
    0.63
    tons
    0.62
     neither
    0.62
     wont
    0.62
    profits
    0.61
     which
    0.60
    Act Density 0.095%

    No Known Activations