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

    Neuronpedia

    INDEX
    Explanations

    terms related to sensitivity and responsiveness in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    stdbool
    -0.59
     pember
    -0.58
    }))
    -0.57
     adequ
    -0.56
     considering
    -0.53
    Swal
    -0.53
    umer
    -0.52
    '))
    -0.49
    وف
    -0.48
    ículo
    -0.47
    POSITIVE LOGITS
     rubrique
    0.71
    HtmlAttribute
    0.64
    fixes
    0.63
     Sos
    0.61
    Sos
    0.60
     Dummies
    0.58
    MENAFN
    0.57
    ckeye
    0.56
    AnchorStyles
    0.56
    orithmic
    0.55
    Act Density 0.025%

    No Known Activations