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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions drawn from evidence or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Usually
    -0.54
     Usually
    -0.51
    usually
    -0.48
    ườn
    -0.44
     уди
    -0.44
     kasarigan
    -0.43
     usually
    -0.43
    FunctionFlags
    -0.43
     spesso
    -0.41
     oc
    -0.41
    POSITIVE LOGITS
     '\\;'
    0.88
     resourceCulture
    0.81
     виправивши
    0.79
    IntoConstraints
    0.79
    fjspx
    0.74
    それとも
    0.68
    -------
    0.67
    ReusableCell
    0.66
    MLLoader
    0.66
     ***!
    0.66
    Act Density 1.216%

    No Known Activations