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

    Neuronpedia

    INDEX
    Explanations

    measurements and units of distance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurement and geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.85
    cloth
    -0.74
    istically
    -0.69
    ãģĦ
    -0.68
    Ctrl
    -0.65
    BIP
    -0.65
     Canary
    -0.65
    isations
    -0.63
    ization
    -0.62
    ammy
    -0.62
    POSITIVE LOGITS
    rals
    1.37
    rogen
    1.35
    rative
    1.35
    rian
    1.35
    rates
    1.35
    ral
    1.28
    rical
    1.27
    rians
    1.27
    rators
    1.26
    rees
    1.25
    Act Density 0.068%

    No Known Activations