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

    Neuronpedia

    INDEX
    Explanations

    the word 'sneak'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "sneak" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -1.00
    rices
    -0.73
    onial
    -0.72
    minus
    -0.71
    nan
    -0.69
    ainers
    -0.65
    acerb
    -0.65
    entric
    -0.64
     Archangel
    -0.64
    relations
    -0.63
    POSITIVE LOGITS
    ily
    1.10
     sneak
    1.06
     peek
    0.95
    door
    0.89
    away
    0.83
     glances
    0.81
    ipeg
    0.76
    iness
    0.74
    ously
    0.74
    iest
    0.74
    Act Density 0.012%

    No Known Activations