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

    Neuronpedia

    INDEX
    Explanations

    various forms of dialogue or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.12
    3:0.13
    4:0.04
    5:0.02
    6:0.17
    7:0.08
    8:0.04
    9:0.07
    10:0.13
    11:0.12
    Negative Logits
    Pg
    -1.52
    ̶
    -1.42
     airports
    -1.38
     neighboring
    -1.36
     HB
    -1.34
     Rapids
    -1.31
     enc
    -1.30
     spawns
    -1.29
     Erie
    -1.27
     Nort
    -1.26
    POSITIVE LOGITS
    NetMessage
    1.77
    java
    1.59
    cffff
    1.57
    cknow
    1.55
    truth
    1.48
     Quote
    1.47
     sincerity
    1.45
    Activity
    1.44
    ldom
    1.42
    reply
    1.41
    Act Density 0.010%

    No Known Activations