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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions performed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions taken in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    been
    -0.69
    arb
    -0.55
    yond
    -0.55
    pex
    -0.54
    money
    -0.53
    copy
    -0.52
     Alley
    -0.52
    por
    -0.52
    itus
    -0.52
    tan
    -0.51
    POSITIVE LOGITS
     yesterday
    0.64
     last
    0.57
     BART
    0.55
     seism
    0.49
     harshly
    0.49
     showc
    0.49
     abruptly
    0.49
     earlier
    0.48
     briefly
    0.47
     Bows
    0.47
    Act Density 0.618%

    No Known Activations