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

    Neuronpedia

    INDEX
    Explanations

    short phrases mentioning a date or time

    oai_token-act-pair · gpt-3.5-turbo

    instances of various article usages and their associated descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ween
    -0.93
    oes
    -0.83
    ngth
    -0.82
    alties
    -0.81
    anas
    -0.79
    seys
    -0.78
    aneers
    -0.78
    chev
    -0.77
    obiles
    -0.76
    opez
    -0.76
    POSITIVE LOGITS
     blatant
    0.77
     moot
    0.69
     continuation
    0.69
     HUGE
    0.69
     DAR
    0.69
     canonical
    0.68
     prol
    0.68
     PvP
    0.68
     VERY
    0.67
     chance
    0.67
    Act Density 0.206%

    No Known Activations