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

    Neuronpedia

    INDEX
    Explanations

    content related to guidance and resource provision in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KeyId
    -0.15
    foy
    -0.14
    æĭħå½ĵ
    -0.14
     Treat
    -0.14
     Möglich
    -0.13
    /umd
    -0.13
     зай
    -0.13
    ìĻ
    -0.12
    STEM
    -0.12
     Corps
    -0.12
    POSITIVE LOGITS
     guide
    0.41
     guides
    0.36
    guide
    0.33
     Guide
    0.32
     guidance
    0.31
     GUIDE
    0.31
    -guide
    0.30
     help
    0.30
     aid
    0.30
     helps
    0.29
    Act Density 0.200%

    No Known Activations