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

    Neuronpedia

    INDEX
    Explanations

    terms related to logical reasoning and rational thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éīĦ
    -0.15
    IRST
    -0.15
    apia
    -0.15
    IBC
    -0.15
     ngang
    -0.14
    eward
    -0.14
    _registered
    -0.14
    aney
    -0.14
    illance
    -0.14
     equalTo
    -0.14
    POSITIVE LOGITS
    fully
    0.17
     Behind
    0.14
    éĢ
    0.14
     lô
    0.14
    oproject
    0.14
     behind
    0.13
    رب
    0.13
     Vac
    0.13
    _construct
    0.13
    nb
    0.13
    Act Density 0.040%

    No Known Activations