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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -0.15
    orts
    -0.14
     Float
    -0.14
    ASI
    -0.14
    iesel
    -0.14
    emia
    -0.13
    aturing
    -0.13
     necessarily
    -0.13
    pora
    -0.13
    dom
    -0.13
    POSITIVE LOGITS
    raft
    0.16
    adians
    0.16
     argument
    0.16
     Wade
    0.15
    694
    0.15
    argument
    0.15
    aus
    0.15
    _COMPAT
    0.15
    argent
    0.15
    CompleteListener
    0.15
    Act Density 0.097%

    No Known Activations