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

    Neuronpedia

    INDEX
    Explanations

    phrases involving transitions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CharacterSet
    -0.14
     Skeleton
    -0.14
    बर
    -0.13
    deen
    -0.13
    .bundle
    -0.13
    VL
    -0.13
    sehen
    -0.13
    ìĻķ
    -0.13
    stant
    -0.13
    jal
    -0.13
    POSITIVE LOGITS
     later
    0.34
    later
    0.27
     eventually
    0.26
     später
    0.26
     latter
    0.24
    Later
    0.23
     Later
    0.23
     soon
    0.22
    å¾Įãģ«
    0.21
     gradually
    0.21
    Act Density 0.144%

    No Known Activations