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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.03
    4:0.04
    5:0.03
    6:0.16
    7:0.03
    8:0.05
    9:0.41
    10:0.02
    11:0.03
    Negative Logits
     Tai
    -4.12
    hack
    -3.60
    iken
    -3.59
    Tai
    -3.42
    zi
    -3.34
     Switzerland
    -3.31
     Bangl
    -3.30
    ieg
    -3.29
    izon
    -3.27
     Tyson
    -3.21
    POSITIVE LOGITS
    Per
    7.22
     Per
    6.89
     PER
    6.64
    per
    6.03
    PER
    5.99
     Perry
    5.61
     Perl
    5.61
     Perkins
    5.14
     Percy
    4.93
     perm
    4.36
    Act Density 0.014%

    No Known Activations