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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and modal verbs indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Î
    -0.15
     sir
    -0.15
    est
    -0.14
    emen
    -0.14
    andle
    -0.14
    ãģĹãĤĩ
    -0.14
     as
    -0.14
    ior
    -0.13
    upa
    -0.13
    estone
    -0.13
    POSITIVE LOGITS
    urse
    0.16
    olley
    0.16
    TYPO
    0.16
    efon
    0.15
     rozh
    0.15
     happen
    0.15
    etal
    0.15
     Broadcasting
    0.14
    atro
    0.14
    cri
    0.14
    Act Density 0.209%

    No Known Activations