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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "began."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rats
    -0.79
    versions
    -0.75
    atching
    -0.75
    oted
    -0.72
    arta
    -0.71
    tan
    -0.70
    road
    -0.68
    iliary
    -0.68
    stood
    -0.68
    atana
    -0.67
    POSITIVE LOGITS
     anew
    0.96
    OPLE
    0.77
     attRot
    0.74
    ĸļ
    0.73
    Ò
    0.72
     [&
    0.72
    CRE
    0.71
    EStream
    0.69
    ITIES
    0.68
     underway
    0.67
    Act Density 0.022%

    No Known Activations