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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases containing the word "slightly"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing slight variations or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.82
     Aviv
    -0.75
    front
    -0.73
     Feast
    -0.70
    emy
    -0.69
    eer
    -0.69
    ilee
    -0.69
    elsen
    -0.68
    velt
    -0.67
    inarily
    -0.66
    POSITIVE LOGITS
     offset
    0.79
     overlap
    0.78
    00007
    0.76
     bump
    0.72
     tang
    0.71
    aditional
    0.68
     audible
    0.66
     inh
    0.66
     tint
    0.66
     incl
    0.66
    Act Density 0.012%

    No Known Activations