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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general statements or overall concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate general statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fax
    -0.79
    Future
    -0.77
    letes
    -0.77
    leted
    -0.75
    lyn
    -0.73
    lete
    -0.67
    XL
    -0.66
    Mount
    -0.65
    mented
    -0.64
    Reb
    -0.64
    POSITIVE LOGITS
     relativity
    1.16
    izations
    0.91
     vicinity
    0.86
    ignment
    0.81
     anesthesia
    0.79
    ization
    0.75
     aviation
    0.75
    edia
    0.74
    arily
    0.71
    isations
    0.69
    Act Density 0.015%

    No Known Activations