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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating concerns about safety and working conditions in a community or workplace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apos
    -0.17
    ptest
    -0.16
    ullan
    -0.15
    .addAction
    -0.14
    pNet
    -0.14
    ecycle
    -0.14
    Ìī
    -0.14
     Griffin
    -0.13
    otta
    -0.13
    agra
    -0.13
    POSITIVE LOGITS
    éĿ
    0.16
     apart
    0.16
    rens
    0.15
    lob
    0.15
     Apart
    0.15
     handjob
    0.15
    Apart
    0.15
    .decorate
    0.14
    ren
    0.14
    Ń
    0.14
    Act Density 0.084%

    No Known Activations