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

    Neuronpedia

    INDEX
    Explanations

    references to following in someone's footsteps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.18
    3:0.05
    4:0.30
    5:0.02
    6:0.07
    7:0.15
    8:0.04
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    hover
    -1.41
    Plex
    -1.39
     Format
    -1.33
    kered
    -1.32
    medium
    -1.32
    question
    -1.30
    DX
    -1.28
    icked
    -1.26
    software
    -1.25
    Media
    -1.23
    POSITIVE LOGITS
     footsteps
    2.17
     herd
    1.58
    abre
    1.56
    verett
    1.48
    roo
    1.44
    utsch
    1.42
    acca
    1.42
    velt
    1.41
     directive
    1.38
    idious
    1.33
    Act Density 0.003%

    No Known Activations