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

    Neuronpedia

    INDEX
    Explanations

    scientific or investigative terms related to analyzing and identifying specific patterns or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identification and tracking of entities or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.81
    --------------------------------------------------------
    -0.71
    addin
    -0.70
    ħĭ
    -0.68
    DES
    -0.68
    amon
    -0.64
    ruary
    -0.61
     Extended
    -0.61
    ustomed
    -0.59
    wark
    -0.59
    POSITIVE LOGITS
     contaminants
    0.91
     offenders
    0.83
     suspicious
    0.81
     entries
    0.81
     stray
    0.81
     excess
    0.78
     traces
    0.77
    bugs
    0.77
     contamin
    0.77
     missing
    0.77
    Act Density 0.897%

    No Known Activations