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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "visit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.06
    4:0.24
    5:0.04
    6:0.04
    7:0.26
    8:0.03
    9:0.03
    10:0.08
    11:0.10
    Negative Logits
     icing
    -1.58
     understatement
    -1.53
    ensical
    -1.45
    autical
    -1.43
     vocals
    -1.42
    eness
    -1.41
    otomy
    -1.40
     juggling
    -1.37
    omial
    -1.36
     blame
    -1.35
    POSITIVE LOGITS
    sites
    2.03
    yrinth
    1.59
     sites
    1.58
    AppData
    1.57
    Site
    1.55
     archives
    1.50
    site
    1.49
     graves
    1.48
     site
    1.48
     Sites
    1.48
    Act Density 0.032%

    No Known Activations