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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disabilities and legal obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.17
     poc
    -0.16
    eway
    -0.16
    CAA
    -0.15
    ovny
    -0.15
    lep
    -0.14
    arrera
    -0.14
     Byrne
    -0.14
    алÑĭ
    -0.14
    osta
    -0.14
    POSITIVE LOGITS
    347
    0.15
     McMahon
    0.15
    677
    0.15
     tempted
    0.15
     bott
    0.15
    247
    0.15
     temptation
    0.14
    .glob
    0.14
    547
    0.14
    åĢĻ
    0.14
    Act Density 0.014%

    No Known Activations