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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a balance of circumstances or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliated
    -0.73
    uilt
    -0.72
    affiliated
    -0.71
    imentary
    -0.70
    etheless
    -0.70
    lav
    -0.68
    sequently
    -0.67
    ordable
    -0.67
    icago
    -0.67
    tions
    -0.67
    POSITIVE LOGITS
     roses
    0.89
     Roses
    0.83
     sheep
    0.78
     Fool
    0.77
     Sheep
    0.75
     Throne
    0.74
     Horses
    0.72
     cake
    0.72
     fools
    0.69
     Mouse
    0.68
    Act Density 1.038%

    No Known Activations