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

    Neuronpedia

    INDEX
    Explanations

    actions or statements related to understanding or purposeful behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions and activities being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mone
    -0.67
    reet
    -0.66
    ases
    -0.66
     laun
    -0.65
    ikers
    -0.65
     Pon
    -0.59
    ©¶æ
    -0.59
     fitting
    -0.58
    asers
    -0.57
    iability
    -0.57
    POSITIVE LOGITS
     here
    0.75
     now
    0.73
    Ø©
    0.73
     tonight
    0.72
     NOW
    0.68
     today
    0.68
    iatus
    0.67
    igating
    0.66
    hani
    0.65
     HERE
    0.63
    Act Density 0.119%

    No Known Activations