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

    Neuronpedia

    INDEX
    Explanations

    references to geographical or conceptual locations and the idea of place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.06
    4:0.13
    5:0.03
    6:0.03
    7:0.39
    8:0.03
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    gery
    -1.58
     saliva
    -1.51
    ecd
    -1.46
    rays
    -1.46
    culosis
    -1.41
     dehydration
    -1.38
     contracted
    -1.36
    ceivable
    -1.36
    phal
    -1.35
    Il
    -1.33
    POSITIVE LOGITS
    ナ
    1.63
    Connector
    1.61
     canon
    1.59
     esteemed
    1.58
    ��
    1.50
    ��
    1.49
     CoC
    1.43
     priorities
    1.42
     galactic
    1.42
     Ranking
    1.41
    Act Density 0.004%

    No Known Activations