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

    Neuronpedia

    INDEX
    Explanations

    references to pain and suffering in a supportive or helpful context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubes
    -0.15
     rid
    -0.14
    372
    -0.14
     intens
    -0.13
    ublic
    -0.13
    .persist
    -0.13
    uring
    -0.13
    á»ĵn
    -0.13
    æŃ²
    -0.13
    .Accessible
    -0.13
    POSITIVE LOGITS
     information
    0.21
    ä¿¡æģ¯
    0.19
     insights
    0.17
    -information
    0.17
     info
    0.17
     INFO
    0.16
     инÑĦоÑĢм
    0.16
    information
    0.16
     INFORMATION
    0.16
    침
    0.16
    Act Density 0.328%

    No Known Activations