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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a focus on specific themes, structures, or concepts within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢек
    -0.16
    ãĥ³ãĥ
    -0.15
    mina
    -0.14
    ursive
    -0.14
    undry
    -0.13
    uckets
    -0.13
    δα
    -0.13
    sel
    -0.13
    itespace
    -0.13
    аÑĢ
    -0.13
    POSITIVE LOGITS
    åŀĭ
    0.15
    ness
    0.14
    pone
    0.14
    _Err
    0.14
    pson
    0.14
    anie
    0.14
    eger
    0.14
    ices
    0.13
    IALOG
    0.13
     Creatures
    0.13
    Act Density 0.082%

    No Known Activations