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

    Neuronpedia

    INDEX
    Explanations

    factual information related to diverse topics and contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.12
    3:0.05
    4:0.05
    5:0.06
    6:0.02
    7:0.09
    8:0.16
    9:0.06
    10:0.18
    11:0.09
    Negative Logits
    uthor
    -0.88
    swer
    -0.85
    byn
    -0.84
    writers
    -0.83
     emerge
    -0.82
     released
    -0.80
    witch
    -0.80
    hops
    -0.77
    swick
    -0.77
    ufact
    -0.77
    POSITIVE LOGITS
    MpServer
    1.00
    vec
    0.99
    �
    0.95
    osexual
    0.88
    ジ
    0.86
     leptin
    0.85
     phenotype
    0.85
    Appearances
    0.85
     rhetorical
    0.82
     mic
    0.82
    Act Density 0.555%

    No Known Activations