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

    Neuronpedia

    INDEX
    Explanations

    references to nonverbal communication and body language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.17
    hea
    -0.16
    ienne
    -0.15
    cales
    -0.15
    awe
    -0.15
     generators
    -0.14
    rina
    -0.14
    ears
    -0.14
    onces
    -0.14
    gom
    -0.14
    POSITIVE LOGITS
    å¥
    0.14
    ocking
    0.14
    ADOS
    0.14
     rust
    0.14
    æĶ¯
    0.14
    mary
    0.14
     Cir
    0.14
    RC
    0.14
    _RC
    0.13
    chas
    0.13
    Act Density 0.212%

    No Known Activations