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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "directly" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    richt
    -0.18
     Herc
    -0.14
    εÏģ
    -0.14
    ufact
    -0.14
    uds
    -0.14
    าร
    -0.14
    psc
    -0.14
    ADVERTISEMENT
    -0.14
    impan
    -0.14
    ÐļÐĺ
    -0.14
    POSITIVE LOGITS
     directly
    0.32
    ivity
    0.32
    direct
    0.24
    ives
    0.24
    rices
    0.24
     direct
    0.24
    ivities
    0.24
     Direct
    0.22
    -direct
    0.22
    Direct
    0.21
    Act Density 0.039%

    No Known Activations