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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility and future actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    radas
    -0.54
     sportifs
    -0.53
     vnto
    -0.52
     précédent
    -0.51
    ség
    -0.51
    lase
    -0.51
     söyledi
    -0.48
    았
    -0.48
    <bos>
    -0.48
    makeatletter
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.86
    AsUp
    0.78
    PreferredItem
    0.75
    Portail
    0.75
     Signalez
    0.73
    HostException
    0.71
     صوتيه
    0.71
    findpost
    0.71
    SourceChecksum
    0.67
    tvguidetime
    0.66
    Act Density 0.064%

    No Known Activations