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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters around symbols like punctuation or special characters

    oai_token-act-pair · gpt-3.5-turbo

    expressions of exasperation or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.82
    ESSION
    -0.78
    lishes
    -0.72
     omission
    -0.67
     redist
    -0.67
     segreg
    -0.64
     prevailing
    -0.64
    ividual
    -0.63
     Samoa
    -0.63
    ACP
    -0.62
    POSITIVE LOGITS
    âĢķ
    1.15
    £
    0.90
    dro
    0.89
    ¹
    0.88
    âĶĢ
    0.80
    âĻ
    0.80
     âĢķ
    0.80
    º
    0.78
    ½
    0.78
    ¯
    0.77
    Act Density 0.360%

    No Known Activations