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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal considerations or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahun
    -0.17
    ahoma
    -0.17
    rale
    -0.15
    145
    -0.15
    gle
    -0.14
    ogui
    -0.14
    ufe
    -0.14
    chal
    -0.14
    tat
    -0.14
    оÑĢÑĤÑĥ
    -0.14
    POSITIVE LOGITS
    озмож
    0.16
    або
    0.16
    edin
    0.14
     later
    0.14
    fit
    0.14
    nable
    0.14
     Gram
    0.13
     Pap
    0.13
    izable
    0.13
    obo
    0.13
    Act Density 0.113%

    No Known Activations