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

    Neuronpedia

    INDEX
    Explanations

    special characters and encoding-related patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate formatting or non-standard text features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.88
    ashtra
    -0.83
    alos
    -0.76
    thumbnails
    -0.74
     Leap
    -0.74
    Reviewer
    -0.69
    */(
    -0.66
    20439
    -0.66
     ESA
    -0.65
    rified
    -0.65
    POSITIVE LOGITS
    ¬¼
    1.20
    Ĥ
    1.17
    §
    1.16
    ¹
    1.14
    ħ
    1.11
    ¦
    1.11
    į
    1.11
    ¶ħ
    1.10
    Ķ
    1.08
    ¬
    1.07
    Act Density 0.004%

    No Known Activations