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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate close physical proximity or direct confrontation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical proximity and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ité
    -0.66
    NESS
    -0.63
    MQ
    -0.61
    sectional
    -0.60
    ossier
    -0.60
    etsk
    -0.59
    ensitive
    -0.59
    FORMATION
    -0.58
    ration
    -0.56
    uation
    -0.56
    POSITIVE LOGITS
    ishly
    1.07
    ously
    1.04
    lessly
    1.01
    wise
    1.01
     wise
    0.97
    ically
    0.92
    ally
    0.91
    arily
    0.90
    aneously
    0.87
    ily
    0.85
    Act Density 0.230%

    No Known Activations