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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or rejection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    patch
    -0.15
    afe
    -0.15
    ondo
    -0.15
    mojom
    -0.15
    OrDefault
    -0.15
    pawn
    -0.14
    å¥ĩ
    -0.14
    visa
    -0.14
    ilder
    -0.14
    onda
    -0.14
    POSITIVE LOGITS
     anymore
    0.18
     any
    0.16
     slightest
    0.14
    arov
    0.14
    ÑģÑĤан
    0.14
     Stats
    0.14
     anyone
    0.14
     Macro
    0.14
     yet
    0.14
    ä»»ä½ķ
    0.14
    Act Density 0.093%

    No Known Activations