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

    Neuronpedia

    INDEX
    Explanations

    references to educational or safety-related organizations and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    екаÑĢ
    -0.16
    .Slf
    -0.15
    iddle
    -0.15
    uco
    -0.14
    afb
    -0.14
    rounded
    -0.14
    bih
    -0.14
    InvalidArgumentException
    -0.14
     bil
    -0.14
    éĽ
    -0.14
    POSITIVE LOGITS
     Sent
    0.28
     Rangers
    0.27
     Ranger
    0.27
     ranger
    0.27
     Power
    0.25
     Bulk
    0.24
    Sent
    0.24
     morph
    0.23
     SENT
    0.23
    Bulk
    0.22
    Act Density 0.008%

    No Known Activations