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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUn
    -0.75
    çĶ°
    -0.67
    è£ħ
    -0.67
     partName
    -0.66
     GP
    -0.64
    racuse
    -0.64
    OSP
    -0.63
     recording
    -0.63
     assemb
    -0.61
    ä¸Ń
    -0.60
    POSITIVE LOGITS
    º
    0.82
    should
    0.81
    Ĵ
    0.80
    ¦
    0.79
    ould
    0.78
    Ń
    0.78
    \'
    0.78
    ¼
    0.77
    ¥
    0.77
    ¬
    0.77
    Act Density 0.309%

    No Known Activations