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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs or phrases indicating action or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nyder
    -0.18
    姿
    -0.15
    æı
    -0.14
    anten
    -0.14
    him
    -0.14
    èĶµ
    -0.13
     Ampl
    -0.13
    ÙĦÙģ
    -0.13
    оÑĢож
    -0.13
     ampl
    -0.13
    POSITIVE LOGITS
     help
    0.25
     enable
    0.23
     allow
    0.22
     better
    0.21
     hopefully
    0.20
     which
    0.19
     suit
    0.18
    /from
    0.18
    gether
    0.18
     support
    0.18
    Act Density 0.236%

    No Known Activations