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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by descriptive phrases or actions that indicate various situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.87
    enhagen
    -0.72
    ilight
    -0.72
    onge
    -0.71
    dinand
    -0.71
    grounds
    -0.69
    ortium
    -0.69
     with
    -0.69
    itially
    -0.68
    licts
    -0.67
    POSITIVE LOGITS
     bang
    1.27
     vengeance
    1.18
     flick
    0.95
     flourish
    0.93
     newfound
    0.91
     impunity
    0.87
     vig
    0.86
     shrug
    0.82
     handshake
    0.79
     limp
    0.77
    Act Density 0.333%

    No Known Activations