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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "one of the."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize specific instances or examples of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hya
    -0.65
    itures
    -0.64
    anse
    -0.62
    enery
    -0.60
    ikarp
    -0.59
    ateurs
    -0.58
    iture
    -0.58
    ynt
    -0.57
    berus
    -0.57
    alez
    -0.57
    POSITIVE LOGITS
    arching
    0.83
    icial
    0.77
     nutshell
    0.74
     course
    0.71
     ours
    0.67
    course
    0.66
     paramount
    0.65
     nic
    0.65
     wonders
    0.64
     hundred
    0.64
    Act Density 0.089%

    No Known Activations