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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the conjunction "or"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions relating to options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rocket
    -0.76
     Cth
    -0.74
     Eid
    -0.72
     Pony
    -0.70
     Tasman
    -0.65
     Gene
    -0.63
    ERAL
    -0.63
     Aqua
    -0.62
    ocracy
    -0.61
     Dian
    -0.61
    POSITIVE LOGITS
    acles
    1.32
    chard
    1.19
    Else
    1.16
    acle
    1.13
    leans
    1.04
    nam
    1.03
    ifice
    1.01
    nery
    1.00
     Marketable
    0.97
    acular
    0.97
    Act Density 0.086%

    No Known Activations