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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utor
    -0.16
    esch
    -0.15
     Pole
    -0.15
    jan
    -0.15
    سط
    -0.14
     typeof
    -0.14
    OUCH
    -0.14
    ecko
    -0.14
    æķ¦
    -0.14
     pole
    -0.14
    POSITIVE LOGITS
    oria
    0.15
    wap
    0.15
     parti
    0.15
    241
    0.14
     inverse
    0.14
     Reverse
    0.14
    place
    0.14
     reverse
    0.14
    bara
    0.14
     Personal
    0.14
    Act Density 0.006%

    No Known Activations