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

    Neuronpedia

    INDEX
    Explanations

    words related to resistance or opposition

    oai_token-act-pair · gpt-3.5-turbo

    words associated with intolerance or insensitivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.85
    mbuds
    -0.79
    displayText
    -0.79
    senal
    -0.78
    pload
    -0.73
    PUT
    -0.73
    sels
    -0.71
    asury
    -0.70
    earchers
    -0.68
    abba
    -0.68
    POSITIVE LOGITS
    ant
    0.99
    antly
    0.92
    ially
    0.87
    ful
    0.83
    ial
    0.81
    aneously
    0.77
    ness
    0.76
    terday
    0.76
    tenance
    0.75
    astic
    0.74
    Act Density 0.020%

    No Known Activations