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

    Neuronpedia

    INDEX
    Explanations

    references to sensitive information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rfloor
    -0.71
     divertimento
    -0.61
     Rowley
    -0.56
     Fortsch
    -0.51
    ppure
    -0.47
    omyia
    -0.46
    logr
    -0.46
     inalámb
    -0.46
     guste
    -0.45
    rok
    -0.45
    POSITIVE LOGITS
     sensitive
    3.58
     Sensitive
    3.45
    Sensitive
    3.29
    sensitive
    3.29
     sensitivity
    3.22
     Sensitivity
    2.92
    sensitivity
    2.81
     sensitivities
    2.68
    Sensitivity
    2.59
     sensi
    2.47
    Act Density 0.078%

    No Known Activations