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

    Neuronpedia

    INDEX
    Explanations

    themes related to conflict and betrayal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĩºåı£
    -0.15
     Sherlock
    -0.14
    agus
    -0.14
    fi
    -0.14
    inf
    -0.13
     ipsum
    -0.13
    hei
    -0.13
    .getApp
    -0.13
    cole
    -0.13
    acob
    -0.13
    POSITIVE LOGITS
    ök
    0.16
    Õ¡
    0.15
    957
    0.14
    kker
    0.14
    436
    0.14
    оÑģлав
    0.14
    203
    0.13
     premise
    0.13
    微软éĽħé»ij
    0.13
    à¥įह
    0.13
    Act Density 0.150%

    No Known Activations