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

    Neuronpedia

    INDEX
    Explanations

    prepositions and auxiliary verbs related to duration and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '},
    -1.17
    ")){
    -1.12
    "):
    -1.08
    "},
    -1.07
    ^(@)
    -1.00
    ".
    -1.00
    `{.
    -0.99
    ſelves
    -0.98
     ?>/
    -0.96
    '),
    -0.96
    POSITIVE LOGITS
    .
    1.44
    ,
    1.28
    ;
    1.27
    !
    1.17
    ?
    0.98
    :
    0.87
    )
    0.77
    。
    0.76
     (
    0.75
    !!
    0.75
    Act Density 0.639%

    No Known Activations