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

    Neuronpedia

    INDEX
    Explanations

    phrases reflecting the significance or recognition of smaller entities or overlooked subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.15
     âĶľ
    -0.15
    ÙĤÙĬÙĤØ©
    -0.15
    exus
    -0.14
    reds
    -0.14
    spar
    -0.14
    &E
    -0.14
    xima
    -0.14
    ANDING
    -0.14
    VERTEX
    -0.14
    POSITIVE LOGITS
     equally
    0.25
    uga
    0.18
    quito
    0.17
    ços
    0.15
    asil
    0.15
     ALSO
    0.15
    ãģ»ãģĨ
    0.14
     gall
    0.14
    ugs
    0.14
     اص
    0.14
    Act Density 0.128%

    No Known Activations