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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs that signify the addition or inclusion of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etre
    -0.18
     ÑĢеб
    -0.15
     hete
    -0.14
    rette
    -0.14
    enter
    -0.14
    strup
    -0.14
     Tre
    -0.13
    -l
    -0.13
    æĬ
    -0.13
    icina
    -0.13
    POSITIVE LOGITS
    igham
    0.17
    uce
    0.16
    iction
    0.14
    chluss
    0.14
    ict
    0.14
    OLON
    0.13
    icted
    0.13
    olon
    0.13
    IEL
    0.13
    onical
    0.13
    Act Density 0.018%

    No Known Activations