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

    Neuronpedia

    INDEX
    Explanations

    specific references to family members in a context

    oai_token-act-pair · gpt-3.5-turbo

    references to family members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.68
    Bridge
    -0.67
    obar
    -0.64
    iti
    -0.63
     wing
    -0.62
    MED
    -0.62
    DEN
    -0.61
    yss
    -0.61
    BAT
    -0.61
     BMC
    -0.61
    POSITIVE LOGITS
    hips
    1.38
    holders
    0.96
    holder
    0.82
    member
    0.78
    hip
    0.76
     Stacy
    0.75
    ertodd
    0.73
    hops
    0.73
    doms
    0.73
     extraord
    0.73
    Act Density 0.032%

    No Known Activations