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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions being taken or events happening

    oai_token-act-pair · gpt-3.5-turbo

    present tense verbs indicating actions or events taking place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underest
    -0.66
    /-
    -0.63
     incorrectly
    -0.63
    ministic
    -0.63
     overest
    -0.62
    lihood
    -0.62
    anon
    -0.61
     hes
    -0.61
     mistake
    -0.60
    wrong
    -0.60
    POSITIVE LOGITS
    ãĤ©
    0.71
    ãĥ¥
    0.63
     redes
    0.60
    FORM
    0.60
     festive
    0.60
    icipated
    0.58
     advoc
    0.58
    veland
    0.57
    ersed
    0.57
    çīĪ
    0.57
    Act Density 0.457%

    No Known Activations