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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "All" and variations related to totality or entirety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    off
    -0.16
    864
    -0.16
    ple
    -0.16
    -ton
    -0.15
    783
    -0.15
    _ED
    -0.15
    ader
    -0.14
    285
    -0.14
    обÑĢаз
    -0.14
     McCorm
    -0.14
    POSITIVE LOGITS
     rights
    0.33
     Rights
    0.31
     RIGHTS
    0.29
     пÑĢава
    0.26
    -rights
    0.23
    Rights
    0.23
    _rights
    0.21
    rights
    0.20
    izard
    0.17
    erdings
    0.17
    Act Density 0.006%

    No Known Activations