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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "set" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "set" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.65
    ible
    -0.64
    aud
    -0.63
    ability
    -0.62
     Occ
    -0.58
    ilee
    -0.58
    Sense
    -0.58
     medial
    -0.58
    alez
    -0.57
    ibility
    -0.57
    POSITIVE LOGITS
    tle
    1.24
     forth
    1.02
     aside
    1.00
     sail
    0.95
     abl
    0.91
     up
    0.83
    tering
    0.79
     showc
    0.75
    rid
    0.75
    tered
    0.75
    Act Density 0.049%

    No Known Activations