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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "contacted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.06
    3:0.07
    4:0.09
    5:0.07
    6:0.08
    7:0.15
    8:0.06
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Opposition
    -1.51
     indigenous
    -1.46
     Mothers
    -1.46
     opposing
    -1.44
     Jama
    -1.41
    ames
    -1.40
     Vim
    -1.39
    aternity
    -1.38
     Brotherhood
    -1.36
     Prosecut
    -1.36
    POSITIVE LOGITS
     lows
    1.54
     clicked
    1.48
     click
    1.47
     deepen
    1.45
     sucked
    1.43
     description
    1.43
    ebin
    1.43
     tuned
    1.41
    click
    1.39
    ptroller
    1.38
    Act Density 0.000%

    No Known Activations