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

    Neuronpedia

    INDEX
    Explanations

    verbs related to diversification or strengthening

    oai_token-act-pair · gpt-3.5-turbo

    words related to categorization and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riter
    -0.68
    dimension
    -0.67
    computer
    -0.66
    erers
    -0.66
    actual
    -0.65
    ranging
    -0.64
    NOT
    -0.64
    bare
    -0.63
    meter
    -0.62
    bill
    -0.62
    POSITIVE LOGITS
    ifies
    0.92
    ifiers
    0.91
    ification
    0.91
    ify
    0.89
    ifying
    0.89
    ainment
    0.89
    rices
    0.87
    undown
    0.86
    ifier
    0.85
    illance
    0.85
    Act Density 0.026%

    No Known Activations