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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strengthening or reinforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of strengthening or supporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.69
    ilk
    -0.67
    76561
    -0.64
    ppers
    -0.64
    ette
    -0.63
    corn
    -0.61
    hair
    -0.60
    hire
    -0.59
    mia
    -0.59
    Spoiler
    -0.59
    POSITIVE LOGITS
    ament
    0.90
     bonds
    0.83
    mble
    0.83
     ties
    0.80
     cohesion
    0.78
    ments
    0.76
     tremend
    0.72
     encryption
    0.71
    atively
    0.71
    hement
    0.70
    Act Density 0.030%

    No Known Activations