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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hesitation or negative responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "don't" or negation

    np_acts-logits-general · gemini-2.0-flash

    don't hesitate or forget

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.58
     Appellants
    -0.55
    хьтан
    -0.54
    actualité
    -0.54
     gddr
    -0.52
     magnética
    -0.50
     outward
    -0.49
    Portale
    -0.49
     Petitioners
    -0.49
     appellants
    -0.49
    POSITIVE LOGITS
     hesitate
    1.22
     hesitated
    0.89
     hés
    0.83
     hesitant
    0.71
     hesit
    0.70
     hesitating
    0.70
     afraid
    0.68
     hesitation
    0.67
     too
    0.65
     shy
    0.63
    Act Density 0.134%

    No Known Activations