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

    Neuronpedia

    INDEX
    Explanations

    instances of significant events or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.16
    urger
    -0.14
    _YUV
    -0.14
    IAM
    -0.14
    444
    -0.14
    ...↵↵
    -0.13
    ÌĢ
    -0.13
    &amp
    -0.13
    ulty
    -0.13
    æı®
    -0.13
    POSITIVE LOGITS
     ,
    0.19
     fuck
    0.18
     ;↵
    0.16
     ;
    0.16
     ,↵
    0.16
     Fucked
    0.15
     fucking
    0.15
     ØĮ
    0.15
     whilst
    0.15
     FUCK
    0.15
    Act Density 0.000%

    No Known Activations