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

    Neuronpedia

    INDEX
    Explanations

    terms related to conferences or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "con."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPS
    -0.76
    terday
    -0.71
    OHN
    -0.71
    Ń·
    -0.69
    İĭ
    -0.63
     wip
    -0.62
     deed
    -0.61
    externalActionCode
    -0.61
     practicable
    -0.60
     hydra
    -0.60
    POSITIVE LOGITS
    stant
    1.16
    ventions
    1.08
    ference
    1.01
    clusions
    0.99
    cept
    0.98
    crete
    0.97
    secut
    0.97
    vention
    0.97
    venient
    0.96
    nex
    0.95
    Act Density 0.012%

    No Known Activations