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

    Neuronpedia

    INDEX
    Explanations

    references to privacy policies and terms of service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cole
    -0.16
    Cole
    -0.15
    284
    -0.15
    cole
    -0.15
     cole
    -0.15
    asar
    -0.15
    ig
    -0.14
    ix
    -0.14
     nude
    -0.14
     above
    -0.14
    POSITIVE LOGITS
    /ag
    0.20
    alic
    0.16
    аниÑĨ
    0.16
    chal
    0.16
     Agreement
    0.15
     Braun
    0.15
     Agree
    0.15
    amma
    0.14
    agos
    0.14
     Moist
    0.14
    Act Density 0.019%

    No Known Activations