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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate design intentions and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /cmd
    -0.15
    wap
    -0.15
    .generated
    -0.15
    hip
    -0.15
    elier
    -0.14
     Koch
    -0.14
    iciar
    -0.14
    .cgi
    -0.13
    öl
    -0.13
    reich
    -0.13
    POSITIVE LOGITS
    ToFit
    0.17
    yı
    0.16
    jem
    0.15
    abi
    0.15
    izik
    0.14
    -designed
    0.14
    vak
    0.14
    акÑģ
    0.14
    zend
    0.14
    rame
    0.14
    Act Density 0.090%

    No Known Activations