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

    Neuronpedia

    INDEX
    Explanations

    phrases related to representation or speaking on behalf of others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    its
    -0.16
    eyed
    -0.16
    lh
    -0.15
    enga
    -0.15
    bits
    -0.15
    bert
    -0.15
    łí
    -0.15
    amac
    -0.15
    ITS
    -0.14
    åł¡
    -0.14
    POSITIVE LOGITS
    soever
    0.22
     behalf
    0.18
    entifier
    0.15
    enty
    0.15
     addCriterion
    0.14
    /javascript
    0.14
    ãĥ³ãĥĨãĤ£
    0.14
    atform
    0.14
    ÏĢά
    0.14
    RuleContext
    0.13
    Act Density 0.009%

    No Known Activations