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

    Neuronpedia

    INDEX
    Explanations

    expressions of anticipation and future intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĦst
    -0.17
    ondon
    -0.15
     fucked
    -0.14
    _MSB
    -0.14
    ibold
    -0.14
    æ§
    -0.14
    BOVE
    -0.14
    ÑģÑĤÑİ
    -0.14
    chine
    -0.14
    kie
    -0.13
    POSITIVE LOGITS
     again
    0.25
     future
    0.25
    future
    0.22
     Future
    0.18
     next
    0.18
    uhl
    0.17
     Again
    0.16
    Future
    0.16
    again
    0.16
    afx
    0.16
    Act Density 0.106%

    No Known Activations