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

    Neuronpedia

    INDEX
    Explanations

    terms related to security and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.85
     CreateTagHelper
    -0.84
    AddTagHelper
    -0.73
    parsedMessage
    -0.68
    ArrowToggle
    -0.66
    WithMany
    -0.65
    fjspx
    -0.65
    Vidite
    -0.64
    хьтан
    -0.64
    Tikang
    -0.64
    POSITIVE LOGITS
    er
    0.66
     guards
    0.58
     coussin
    0.57
    Scorecard
    0.54
     guard
    0.54
     against
    0.52
     Brenner
    0.51
     tightened
    0.50
     Guards
    0.49
     Blanket
    0.49
    Act Density 0.072%

    No Known Activations