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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a personal perspective or knowledge of a situation

    oai_token-act-pair · gpt-3.5-turbo

    statements related to personal awareness and expression of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..............
    -0.75
    çļ
    -0.72
    omas
    -0.67
     Centauri
    -0.67
    ++++
    -0.66
     Miko
    -0.66
     Tanz
    -0.64
     ACTIONS
    -0.63
     Cros
    -0.62
    rete
    -0.60
    POSITIVE LOGITS
     ascertain
    0.74
     recollection
    0.73
     interpret
    0.73
     interpretation
    0.72
    eding
    0.71
     approximation
    0.71
    bender
    0.70
    ced
    0.69
    mercial
    0.68
    aches
    0.67
    Act Density 0.116%

    No Known Activations