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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    strings of alphanumeric characters and specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.76
     streng
    -0.68
    comb
    -0.67
     Excellence
    -0.67
    antha
    -0.66
    theless
    -0.66
     behavi
    -0.63
     withd
    -0.61
     compulsion
    -0.60
     Lauder
    -0.60
    POSITIVE LOGITS
    wl
    0.85
     dstg
    0.84
    qq
    0.83
    xb
    0.79
    bsp
    0.79
    fm
    0.78
    vr
    0.77
    xd
    0.77
    dn
    0.75
    cd
    0.75
    Act Density 0.278%

    No Known Activations