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

    Neuronpedia

    INDEX
    Explanations

    references to legal cases and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.57
    educated
    -0.54
     among
    -0.54
    ung
    -0.54
     distinguishes
    -0.54
    earchers
    -0.54
    atellite
    -0.53
    spoken
    -0.53
    aily
    -0.51
    onia
    -0.51
    POSITIVE LOGITS
    )).
    0.79
    ]).
    0.70
     previous
    0.66
     Wiz
    0.65
     aforementioned
    0.64
     fame
    0.61
     CP
    0.61
     inception
    0.60
     LW
    0.58
     totality
    0.58
    Act Density 0.994%

    No Known Activations