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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-doubt and vulnerability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äºĪ
    -0.19
    ignon
    -0.17
    ätz
    -0.15
    angi
    -0.15
    scar
    -0.14
    OLUTE
    -0.14
    auer
    -0.14
    ůž
    -0.14
    Ignoring
    -0.14
     )↵↵↵↵↵↵↵↵
    -0.13
    POSITIVE LOGITS
     doubts
    0.27
     doubt
    0.25
     feelings
    0.24
     insecure
    0.23
     feeling
    0.22
     doub
    0.22
     Doub
    0.21
     inse
    0.21
     internal
    0.20
     feels
    0.20
    Act Density 0.285%

    No Known Activations