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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or anticipation regarding future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĪ
    -0.15
    imedia
    -0.15
    iek
    -0.14
    AZE
    -0.14
    -regexp
    -0.14
    prung
    -0.14
    iqueta
    -0.14
    alars
    -0.14
    inho
    -0.14
    bee
    -0.14
    POSITIVE LOGITS
    åĪ·
    0.17
    XL
    0.16
    UNIT
    0.15
    bsolute
    0.14
    pty
    0.14
    much
    0.14
    lo
    0.13
     åij¨
    0.13
    åľĺ
    0.13
    mostly
    0.13
    Act Density 0.078%

    No Known Activations