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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.73
    expandindo
    -0.72
    +#+
    -0.62
     Jefus
    -0.59
     Taktlose
    -0.54
    
    -0.53
     houſe
    -0.53
    oa̍t
    -0.52
     myſelf
    -0.52
     garantías
    -0.50
    POSITIVE LOGITS
     forced
    0.55
     Forced
    0.54
     az
    0.49
     forcing
    0.48
     Guy
    0.44
    잖
    0.43
    forced
    0.43
     Prima
    0.41
     guy
    0.41
    rop
    0.40
    Act Density 0.216%

    No Known Activations