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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to actions taken or steps in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erve
    -0.16
    .za
    -0.15
    imits
    -0.15
    pq
    -0.15
    cores
    -0.15
    tg
    -0.14
    lid
    -0.14
    sak
    -0.14
    -blood
    -0.14
    lags
    -0.14
    POSITIVE LOGITS
    wise
    0.34
     taken
    0.33
     forward
    0.32
     Taken
    0.30
    éª
    0.28
    Taken
    0.27
    taken
    0.26
     Forward
    0.25
    -by
    0.25
    -wise
    0.23
    Act Density 0.026%

    No Known Activations