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

    Neuronpedia

    INDEX
    Explanations

    phrases related to combining different elements or factors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate combinations or pairings of elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chat
    -0.77
    endant
    -0.75
    ister
    -0.74
    ike
    -0.72
    lesh
    -0.70
    deen
    -0.67
    ndra
    -0.66
    Discuss
    -0.66
    asley
    -0.65
    ambers
    -0.65
    POSITIVE LOGITS
    ++++++++
    0.77
     impunity
    0.75
     occasional
    0.71
     accompanying
    0.68
    eely
    0.65
     superst
    0.65
     layers
    0.62
     observations
    0.62
     myriad
    0.62
     hindsight
    0.62
    Act Density 0.082%

    No Known Activations