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

    Neuronpedia

    INDEX
    Explanations

    words expressing a change or transition happening over time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.63
    Height
    -0.63
    ername
    -0.62
    Percent
    -0.61
    ctors
    -0.60
     Guilty
    -0.60
    HAEL
    -0.60
    EStreamFrame
    -0.59
    ="#
    -0.59
    AX
    -0.57
    POSITIVE LOGITS
    been
    0.96
    stood
    0.81
    ked
    0.76
    grown
    0.74
    ayed
    0.72
    oured
    0.71
     abundance
    0.70
    umption
    0.67
     been
    0.64
    urred
    0.63
    Act Density 0.146%

    No Known Activations