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

    Neuronpedia

    INDEX
    Explanations

    words that indicate existential concerns or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quist
    -0.14
    olt
    -0.14
    аÑĤе
    -0.14
     hus
    -0.14
    bart
    -0.14
     Reply
    -0.14
    aida
    -0.13
    raid
    -0.13
     different
    -0.13
    jav
    -0.13
    POSITIVE LOGITS
    å®ŀéĻħ
    0.16
    HeaderCode
    0.16
    ÅĽ
    0.15
     actually
    0.15
    DNA
    0.14
    etto
    0.14
    _actual
    0.14
    èĬ³
    0.14
    .ci
    0.14
    ึà¸ģ
    0.14
    Act Density 0.004%

    No Known Activations