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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or actions in a given situation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "when" indicating conditions or timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.76
    gem
    -0.67
    rolet
    -0.65
    Lay
    -0.65
    ãĤ«
    -0.63
    gur
    -0.63
    athom
    -0.63
    sonian
    -0.62
    hole
    -0.62
    alin
    -0.62
    POSITIVE LOGITS
    soever
    1.42
    irlf
    0.86
     confronted
    0.84
    */(
    0.78
     faced
    0.76
     pressed
    0.75
     asked
    0.75
     comparing
    0.73
     encountering
    0.70
     subjected
    0.69
    Act Density 0.134%

    No Known Activations