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

    Neuronpedia

    INDEX
    Explanations

    terms related to motivation and motivational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hole
    -0.17
    hone
    -0.17
    ESIS
    -0.16
    atura
    -0.16
    ialog
    -0.16
    halt
    -0.16
    ITES
    -0.15
    eda
    -0.15
    hos
    -0.15
    oje
    -0.15
    POSITIVE LOGITS
    ivation
    0.37
    ivated
    0.35
    ley
    0.33
    ivating
    0.31
    oring
    0.30
    own
    0.29
    ivate
    0.29
    ives
    0.25
    tram
    0.25
    ifs
    0.25
    Act Density 0.010%

    No Known Activations