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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or strategies in handling various situations

    oai_token-act-pair · gpt-3.5-turbo

    words associated with systems and processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.65
     clin
    -0.63
     suppose
    -0.60
     Looking
    -0.60
     viz
    -0.59
    \'
    -0.56
     headlined
    -0.56
     rocked
    -0.55
     anchored
    -0.55
    sectional
    -0.54
    POSITIVE LOGITS
    lessly
    1.23
    ulate
    1.13
    ify
    1.11
    orously
    0.97
    uate
    0.93
    ize
    0.92
    imize
    0.92
    ise
    0.90
    matically
    0.88
    ishly
    0.87
    Act Density 0.394%

    No Known Activations