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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or first occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    014
    -0.17
    oyo
    -0.16
    haus
    -0.15
    лим
    -0.14
    .Named
    -0.14
    .syntax
    -0.14
    _CHARSET
    -0.14
    nce
    -0.13
    eslint
    -0.13
    eteria
    -0.13
    POSITIVE LOGITS
     kind
    0.49
     type
    0.41
    kind
    0.36
     sort
    0.32
    .kind
    0.32
    type
    0.31
    _kind
    0.30
    -kind
    0.29
    	type
    0.28
    .type
    0.28
    Act Density 0.029%

    No Known Activations