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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the gradual or frequent occurrence of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to occurrences or events happening in general

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.77
     helm
    -0.75
     overse
    -0.71
    ebted
    -0.69
    iction
    -0.69
    ngth
    -0.66
     endors
    -0.66
    otton
    -0.65
    uling
    -0.65
    ielding
    -0.64
    POSITIVE LOGITS
     millisec
    0.85
     milliseconds
    0.79
     occurrences
    0.78
     happen
    0.72
     happ
    0.68
     Rodrig
    0.67
     happening
    0.67
    actly
    0.67
     coinc
    0.67
    ï¸
    0.67
    Act Density 0.445%

    No Known Activations