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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings followed by special characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    details about technical specifications or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.76
    ciating
    -0.73
     princ
    -0.72
     ric
    -0.72
     cher
    -0.69
     scient
    -0.67
    iform
    -0.65
     sausage
    -0.64
     laun
    -0.63
     dove
    -0.62
    POSITIVE LOGITS
    E
    1.69
    B
    1.63
    F
    1.63
    C
    1.61
    R
    1.56
    L
    1.55
    T
    1.54
    P
    1.54
    N
    1.54
    D
    1.53
    Act Density 0.172%

    No Known Activations