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

    Neuronpedia

    INDEX
    Explanations

    numbers and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the word "slightly" and its variations, indicating nuances or moderate changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.78
     Aviv
    -0.76
    emy
    -0.74
    velt
    -0.72
    elsen
    -0.70
    front
    -0.68
    yers
    -0.67
     Feast
    -0.67
    uments
    -0.65
    ¥µ
    -0.65
    POSITIVE LOGITS
     offset
    0.81
     overlap
    0.79
     tint
    0.73
     tang
    0.72
    00007
    0.69
     inaccurate
    0.69
     incl
    0.68
    otropic
    0.68
     insignificant
    0.68
    aditional
    0.67
    Act Density 0.012%

    No Known Activations