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

    Neuronpedia

    INDEX
    Explanations

    indicative phrases and statements that signal significance or importance in an argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.77
     LNB
    -0.74
     Herodotus
    -0.73
     Ptole
    -0.72
    󠁢
    -0.72
    TintMode
    -0.70
     Agamemnon
    -0.69
     Majefty
    -0.69
     Hyperion
    -0.67
    OGND
    -0.67
    POSITIVE LOGITS
     the
    1.11
     those
    0.93
    those
    0.66
     a
    0.63
    namely
    0.61
     called
    0.61
     Those
    0.60
     our
    0.59
    though
    0.59
     aqueles
    0.58
    Act Density 0.245%

    No Known Activations