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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a topic or issue being brought up or discussed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ially
    -0.76
    gee
    -0.71
    ritical
    -0.71
    robe
    -0.69
     CLSID
    -0.67
    reat
    -0.65
    ow
    -0.61
    otta
    -0.61
    pi
    -0.60
    closure
    -0.59
    POSITIVE LOGITS
    river
    0.84
     sooner
    0.74
     somewhere
    0.74
     everywhere
    0.72
     elsewhere
    0.69
    BACK
    0.68
     spontaneously
    0.68
     Caller
    0.65
     anywhere
    0.65
     nowhere
    0.65
    Act Density 0.060%

    No Known Activations