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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of media and their impact on personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation or the word "as"

    np_acts-logits-general · gemini-2.0-flash

    judging or considering things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obviously
    -0.70
    obviously
    -0.64
     Obviously
    -0.59
    Obviously
    -0.56
     évidemment
    -0.50
    显然
    -0.48
     ofc
    -0.48
     oczywiście
    -0.47
     obviamente
    -0.46
     ovviamente
    -0.46
    POSITIVE LOGITS
     judging
    0.74
     мәкал
    0.63
     🤔
    0.63
    ंदीखरीदारी
    0.63
     zumindest
    0.62
     considering
    0.61
     tbh
    0.61
    それとも
    0.58
    considering
    0.58
    oneofs
    0.58
    Act Density 0.660%

    No Known Activations