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

    Neuronpedia

    INDEX
    Explanations

    references to people and their struggles or various predicaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostel
    -0.17
    arin
    -0.15
    empo
    -0.15
    ulumi
    -0.14
    öst
    -0.14
    uge
    -0.14
    stab
    -0.14
    osit
    -0.14
    REAK
    -0.14
    affen
    -0.14
    POSITIVE LOGITS
     vulnerable
    0.25
     feeling
    0.24
     with
    0.24
     Vulner
    0.21
     without
    0.21
     exposed
    0.19
     stranded
    0.19
     to
    0.18
     vulner
    0.18
    Exposed
    0.18
    Act Density 0.055%

    No Known Activations