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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenges or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "all" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.90
    lished
    -0.82
     tremend
    -0.75
    yip
    -0.71
    hered
    -0.69
    cffff
    -0.69
     estab
    -0.69
    dyl
    -0.68
     slightest
    -0.65
    SHIP
    -0.65
    POSITIVE LOGITS
    owing
    1.17
    enged
    1.14
    enge
    1.10
    ocated
    1.09
    adium
    1.07
    iance
    1.05
    ocation
    1.03
    enges
    1.02
    ength
    1.01
    ocations
    1.01
    Act Density 0.026%

    No Known Activations