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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direct actions or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #ac
    -0.14
    -ending
    -0.14
    iro
    -0.14
    ReadStream
    -0.14
    ester
    -0.14
    ena
    -0.14
    atre
    -0.14
    ÑĢина
    -0.14
    κÏģα
    -0.14
    _PHY
    -0.13
    POSITIVE LOGITS
     directly
    0.25
    direct
    0.23
     direct
    0.23
     Direct
    0.23
    Direct
    0.21
     DIRECT
    0.19
    DIRECT
    0.18
    _direct
    0.18
    -direct
    0.17
    omid
    0.17
    Act Density 0.073%

    No Known Activations