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

    Neuronpedia

    INDEX
    Explanations

    instances of past tense verbs indicating positive experiences or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    currently
    -0.23
     currently
    -0.22
     now
    -0.19
     presently
    -0.19
    Currently
    -0.18
     Currently
    -0.17
    iani
    -0.15
    ãĥ«ãĥķ
    -0.15
     maintenant
    -0.15
     STILL
    -0.15
    POSITIVE LOGITS
     yesterday
    0.18
     Yesterday
    0.18
    /is
    0.17
     fork
    0.16
     originally
    0.15
     Fork
    0.15
    abi
    0.14
    Yesterday
    0.14
     analog
    0.14
     inevitable
    0.13
    Act Density 0.159%

    No Known Activations