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

    Neuronpedia

    INDEX
    Explanations

    dates in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    structured information related to scheduling and event listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifes
    -0.82
     bailout
    -0.75
     inadequ
    -0.74
     escaping
    -0.74
     clamp
    -0.73
     somew
    -0.72
     damned
    -0.71
     motiv
    -0.71
     betting
    -0.70
     scripting
    -0.70
    POSITIVE LOGITS
    Rank
    1.01
    Notable
    0.98
    Original
    0.94
    ------------------------
    0.94
    ãĤ¨ãĥ«
    0.93
    Below
    0.90
    ----------------
    0.90
    ----------------------------------------------------------------
    0.90
    ################
    0.89
    Sel
    0.89
    Act Density 0.197%

    No Known Activations