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

    Neuronpedia

    INDEX
    Explanations

    references to specific terms or names indicated by the word "Dot", with varying degrees of activation for different variations of this term

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Dot" and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iscopal
    -0.73
     obser
    -0.70
    reditary
    -0.69
    uberty
    -0.68
    ivals
    -0.67
     Belief
    -0.65
    eatures
    -0.65
    HB
    -0.62
    issance
    -0.62
    éĹĺ
    -0.61
    POSITIVE LOGITS
    zeb
    0.94
     Dot
    0.92
    wana
    0.83
    zh
    0.80
    forth
    0.77
    dot
    0.76
    rice
    0.75
    amphetamine
    0.75
    TY
    0.71
    lings
    0.68
    Act Density 0.016%

    No Known Activations