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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical details and specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various scientific and technological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.72
    orum
    -0.65
    orget
    -0.63
    Semitism
    -0.62
    ISTORY
    -0.61
    uctions
    -0.61
    ibraries
    -0.60
    cyclopedia
    -0.60
    anners
    -0.60
    legraph
    -0.59
    POSITIVE LOGITS
     oriented
    1.34
     friendly
    1.25
    less
    1.21
    able
    1.14
    -
    1.12
    based
    1.12
     compliant
    1.10
     sized
    1.09
     driven
    1.08
    worthy
    1.08
    Act Density 0.847%

    No Known Activations