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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing anticipation or curiosity towards future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing curiosity or interest about observations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ById
    -0.75
     disappeared
    -0.69
     disappearing
    -0.68
     retracted
    -0.65
     quitting
    -0.65
     waived
    -0.64
     vanished
    -0.64
     cance
    -0.63
     resignation
    -0.63
    selves
    -0.63
    POSITIVE LOGITS
     see
    1.38
     hear
    1.28
     speculate
    1.23
     revisit
    1.21
     explore
    1.19
     examine
    1.17
     compare
    1.14
     ponder
    1.14
     learn
    1.14
     observe
    1.11
    Act Density 0.140%

    No Known Activations