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

    Neuronpedia

    INDEX
    Explanations

    references to cultural or societal norms and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owa
    -0.15
     Sat
    -0.14
     units
    -0.14
     advance
    -0.14
     Nur
    -0.13
    ony
    -0.13
    aire
    -0.13
     Adapt
    -0.13
    athy
    -0.13
    an
    -0.13
    POSITIVE LOGITS
    ewire
    0.19
     aquÃŃ
    0.19
    .ie
    0.18
    è¿ĻéĩĮ
    0.17
     here
    0.17
    icha
    0.17
    ancel
    0.16
    cio
    0.16
    ãģĵãģĵ
    0.16
    _here
    0.15
    Act Density 0.455%

    No Known Activations