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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "bookmark"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wages
    -0.67
    apist
    -0.65
     decomp
    -0.65
    agan
    -0.65
    ADS
    -0.63
    azar
    -0.63
    agin
    -0.60
     overcome
    -0.60
    QUI
    -0.59
    ibaba
    -0.58
    POSITIVE LOGITS
    mark
    1.01
    manship
    0.97
    eer
    0.96
    tenance
    0.96
    marks
    0.95
    hyde
    0.95
    furt
    0.90
    eters
    0.87
    emark
    0.84
    /-
    0.82
    Act Density 0.022%

    No Known Activations