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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating potential situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that express hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Els
    -0.76
    OPLE
    -0.75
    Rated
    -0.62
    OWN
    -0.61
    SPONSORED
    -0.60
     Canary
    -0.56
    Cu
    -0.55
    OTO
    -0.55
    arsity
    -0.55
    oller
    -0.55
    POSITIVE LOGITS
     disclaim
    0.75
    math
    0.65
    claimer
    0.61
    ndra
    0.59
     tc
    0.59
     sv
    0.58
    apor
    0.58
    otal
    0.57
    ertain
    0.56
    estial
    0.56
    Act Density 0.112%

    No Known Activations