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

    Neuronpedia

    INDEX
    Explanations

    instances of reaching a limit or threshold related to a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asso
    -0.16
    .annotations
    -0.15
     NAT
    -0.15
    azor
    -0.15
    chg
    -0.14
    agna
    -0.14
    arakter
    -0.14
    018
    -0.14
    ös
    -0.14
    burger
    -0.13
    POSITIVE LOGITS
    egra
    0.16
    edla
    0.15
    leton
    0.14
    too
    0.14
    hend
    0.14
    _lineno
    0.14
    ê´ij
    0.13
    loub
    0.13
    çĴĥ
    0.13
    letal
    0.13
    Act Density 0.502%

    No Known Activations