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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    specific repeated characters or sequences within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.81
     disadvant
    -0.79
     informants
    -0.69
     sacrific
    -0.69
     incorpor
    -0.69
     proxies
    -0.68
     obser
    -0.66
     imitation
    -0.65
     intercept
    -0.65
     advant
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.31
    ï¸
    1.01
    iversary
    0.96
    à¥
    0.82
    VERTISEMENT
    0.79
    ¯¯
    0.78
    ship
    0.77
    âĤ¬
    0.76
    eric
    0.75
     onwards
    0.74
    Act Density 0.278%

    No Known Activations