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

    Neuronpedia

    INDEX
    Explanations

    phrases related to short-lived or temporary situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases indicating short-lived experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.74
     Cah
    -0.74
    ibus
    -0.67
     clause
    -0.67
     solicitation
    -0.65
    iatus
    -0.64
     SHARES
    -0.64
     aftermath
    -0.64
     Caucasus
    -0.64
     Discipline
    -0.63
    POSITIVE LOGITS
    compatible
    1.05
    eligible
    1.03
    tested
    1.03
    enough
    1.02
    eyed
    1.01
    heartedly
    1.01
    functional
    1.00
    years
    0.97
    grown
    0.96
    handedly
    0.96
    Act Density 0.205%

    No Known Activations