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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating similarities or comparisons between different subjects or objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparisons between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Published
    -0.66
    mberg
    -0.54
    fre
    -0.53
     Guth
    -0.53
    Dispatch
    -0.53
    unes
    -0.51
    uff
    -0.51
    mans
    -0.50
    orts
    -0.50
    clamation
    -0.50
    POSITIVE LOGITS
     to
    0.92
     thereto
    0.90
     twins
    0.87
    lihood
    0.87
    ively
    0.79
    ities
    0.78
     unto
    0.76
     sized
    0.74
    ĸļ
    0.71
    worldly
    0.70
    Act Density 0.068%

    No Known Activations