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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases expressing hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĢη
    -0.17
     Quarter
    -0.15
    ipline
    -0.14
     Cur
    -0.14
    indle
    -0.14
     since
    -0.14
     Succ
    -0.13
    aceae
    -0.13
    ider
    -0.13
     bo
    -0.13
    POSITIVE LOGITS
    only
    0.22
     only
    0.20
    _only
    0.18
     seulement
    0.18
     wishes
    0.16
     ONLY
    0.16
     Only
    0.16
    _ONLY
    0.15
    Only
    0.15
    ONLY
    0.15
    Act Density 0.066%

    No Known Activations