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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative characteristics or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovember
    -0.92
    ainers
    -0.85
    osponsors
    -0.83
    mberg
    -0.81
    ernels
    -0.81
    orthy
    -0.76
    chwitz
    -0.72
    different
    -0.71
    ADA
    -0.71
    emis
    -0.71
    POSITIVE LOGITS
    ly
    0.97
    ness
    0.91
     nature
    0.90
     impulse
    0.86
     tendencies
    0.86
     pursuit
    0.83
     impulses
    0.80
     glances
    0.80
     gaze
    0.79
     streak
    0.78
    Act Density 0.135%

    No Known Activations