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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antz
    -0.15
    غاÙĦ
    -0.15
    avery
    -0.14
    ::$
    -0.13
    ADS
    -0.13
    cpt
    -0.13
    нок
    -0.13
    帮
    -0.13
    cplusplus
    -0.12
    ENABLE
    -0.12
    POSITIVE LOGITS
     say
    0.96
     saying
    0.89
     says
    0.79
     said
    0.79
    say
    0.76
    说
    0.73
     Say
    0.71
     SAY
    0.68
    Say
    0.68
    .say
    0.63
    Act Density 0.447%

    No Known Activations