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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to forts

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.93
    interstitial
    -0.85
    jriwal
    -0.73
    adesh
    -0.73
    STEM
    -0.69
    jack
    -0.68
    externalActionCode
    -0.66
    DER
    -0.65
    CHAT
    -0.63
    Jacob
    -0.63
    POSITIVE LOGITS
    resses
    0.89
    eur
    0.88
     Lauderdale
    0.88
    fort
    0.88
    ress
    0.88
    uitous
    0.84
    inho
    0.83
    orious
    0.82
    oise
    0.82
    ieth
    0.81
    Act Density 0.024%

    No Known Activations