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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'obvious' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aur
    -0.17
    ronics
    -0.15
    ola
    -0.15
    istrovstvÃŃ
    -0.15
    leÅŁik
    -0.15
    -↵↵
    -0.15
    yb
    -0.15
    _VERBOSE
    -0.15
    æĮĻ
    -0.15
    bjerg
    -0.14
    POSITIVE LOGITS
    mente
    0.29
    ness
    0.26
    ly
    0.23
    LY
    0.21
    ging
    0.20
    antt
    0.19
    ely
    0.18
     enough
    0.18
    NESS
    0.17
     rÃłng
    0.17
    Act Density 0.032%

    No Known Activations