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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action

    oai_token-act-pair · gpt-3.5-turbo

    key action verbs and phrases that imply representation or consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cium
    -0.73
    AX
    -0.70
    Contin
    -0.70
    iband
    -0.60
    ibu
    -0.60
    ombat
    -0.59
    enium
    -0.59
    GO
    -0.58
    iber
    -0.58
    nen
    -0.58
    POSITIVE LOGITS
     theirs
    1.83
     hers
    1.68
     yours
    1.49
     ours
    1.48
     mine
    1.33
     his
    1.25
    his
    1.22
     your
    1.15
    their
    1.11
     my
    1.11
    Act Density 0.464%

    No Known Activations