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

    Neuronpedia

    INDEX
    Explanations

    instances where a minimum threshold or level is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a minimum requirement or threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tions
    -0.77
    rats
    -0.65
    quit
    -0.63
    icides
    -0.62
    kai
    -0.62
    omics
    -0.61
    ãĤ¿
    -0.60
    oris
    -0.60
     Dynamics
    -0.60
     deletion
    -0.60
    POSITIVE LOGITS
     partially
    0.98
     partly
    0.92
     SOME
    0.86
    lik
    0.79
     temporarily
    0.78
     moderately
    0.75
     marginally
    0.75
     mildly
    0.72
     somewhat
    0.70
     partial
    0.70
    Act Density 0.032%

    No Known Activations