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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance or input from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.15
     Citation
    -0.15
    enheim
    -0.15
    imli
    -0.15
    jÃł
    -0.15
    yne
    -0.14
    avage
    -0.14
    olik
    -0.14
    Binder
    -0.14
     leve
    -0.13
    POSITIVE LOGITS
     cooperation
    0.19
     help
    0.18
     attention
    0.17
    attention
    0.16
     opinion
    0.16
    sey
    0.15
     input
    0.15
    éħįåIJĪ
    0.15
     thoughts
    0.14
    èĪį
    0.14
    Act Density 0.090%

    No Known Activations