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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and relationships within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Punch
    -0.15
    iros
    -0.14
    _patch
    -0.14
    ामन
    -0.14
    shell
    -0.14
    avou
    -0.14
     shell
    -0.14
    Å¡ov
    -0.14
    ůst
    -0.13
    ÄĽj
    -0.13
    POSITIVE LOGITS
    åıĬåħ¶
    0.19
    /her
    0.17
    Ư
    0.15
    ÑĤин
    0.15
    ationToken
    0.15
    коз
    0.15
    /bower
    0.15
    моÑģ
    0.14
    .sendFile
    0.14
    ëħ
    0.14
    Act Density 0.116%

    No Known Activations