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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating membership or participation in events or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emplates
    -0.14
    .overflow
    -0.12
    ervations
    -0.12
    ivot
    -0.12
    agos
    -0.12
    adele
    -0.12
     transmitting
    -0.12
    ipherals
    -0.12
    зем
    -0.12
    assis
    -0.12
    POSITIVE LOGITS
     receive
    0.38
     benefit
    0.34
     receives
    0.34
     qualify
    0.32
     automatically
    0.32
     rec
    0.31
     enjoy
    0.31
     get
    0.31
    receive
    0.30
     reap
    0.30
    Act Density 0.157%

    No Known Activations