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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or state of individuals or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.84
     anniversary
    -0.64
    poke
    -0.63
    icio
    -0.61
    igion
    -0.61
    brance
    -0.58
    entials
    -0.58
    sche
    -0.58
    iversary
    -0.57
    rawdownloadcloneembedreportprint
    -0.57
    POSITIVE LOGITS
     abound
    0.98
    ŃĶ
    0.93
     alike
    0.89
     seldom
    0.89
     rarely
    0.85
     prolifer
    0.84
     often
    0.80
    entimes
    0.79
     tended
    0.79
     always
    0.78
    Act Density 0.556%

    No Known Activations