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

    Neuronpedia

    INDEX
    Explanations

    terms related to increasing stakes or intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing stakes or intensity in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HRC
    -0.82
     Wanted
    -0.74
     Shades
    -0.72
     Flavoring
    -0.70
    Assembly
    -0.70
    KNOWN
    -0.66
    ï¸ı
    -0.65
    aiman
    -0.65
     Drawn
    -0.64
     Citizens
    -0.64
    POSITIVE LOGITS
     ante
    1.39
    pole
    1.02
    phrine
    0.83
    bell
    0.81
    mun
    0.78
    vent
    0.77
    reon
    0.76
     quo
    0.76
     pse
    0.75
    mortem
    0.75
    Act Density 0.009%

    No Known Activations