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

    Neuronpedia

    INDEX
    Explanations

    numbers representing statistical data or measurements

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and numerical representations related to various measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.60
     organising
    -0.54
    DragonMagazine
    -0.54
     newcom
    -0.51
    GoldMagikarp
    -0.50
     GOODMAN
    -0.50
    achine
    -0.49
    zens
    -0.49
    »Ĵ
    -0.48
     Replay
    -0.47
    POSITIVE LOGITS
    .
    1.10
    .,
    1.01
    .;
    0.93
    .?
    0.90
    ./
    0.89
    ._
    0.81
    .:
    0.80
    .,"
    0.76
    ½
    0.75
    .-
    0.75
    Act Density 0.098%

    No Known Activations