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

    Neuronpedia

    INDEX
    Explanations

    terms related to speed, immediacy, and urgency

    oai_token-act-pair · gpt-3.5-turbo

    words related to measurement or balance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Christensen
    -0.63
     Dani
    -0.62
     Kro
    -0.60
     Dawkins
    -0.60
    LET
    -0.60
    00007
    -0.58
     Chains
    -0.58
     Ambro
    -0.57
     Vog
    -0.57
     themed
    -0.57
    POSITIVE LOGITS
    cised
    1.00
    inence
    0.95
    achable
    0.95
    achment
    0.93
    inately
    0.93
    ably
    0.86
    itent
    0.84
    teness
    0.84
    abil
    0.84
    cient
    0.82
    Act Density 0.062%

    No Known Activations