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

    Neuronpedia

    INDEX
    Explanations

    mentions of credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergic
    -0.14
    yny
    -0.14
    erman
    -0.14
    atte
    -0.14
    cky
    -0.14
    ÑĩиÑģ
    -0.14
    för
    -0.14
    ágenes
    -0.13
    erule
    -0.13
    drive
    -0.13
    POSITIVE LOGITS
    ible
    0.26
    ulous
    0.25
    ibility
    0.24
    ibly
    0.24
    itor
    0.23
    ence
    0.21
    encia
    0.20
    ITOR
    0.20
    ibilit
    0.20
    encial
    0.19
    Act Density 0.006%

    No Known Activations