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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with sensitivity and specific vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rfloor
    -0.58
     crows
    -0.58
     Stornier
    -0.58
     crow
    -0.58
    wyk
    -0.57
     Fact
    -0.57
     fraî
    -0.56
     Crowley
    -0.56
    richtet
    -0.55
     Boyce
    -0.54
    POSITIVE LOGITS
     sensitive
    2.03
     Sensitive
    2.02
    Sensitive
    1.93
    sensitive
    1.81
     sensitivity
    1.74
     sensitivities
    1.62
     Sensitivity
    1.62
     sensi
    1.60
    ensitive
    1.50
    Sensitivity
    1.50
    Act Density 0.161%

    No Known Activations