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

    Neuronpedia

    INDEX
    Explanations

    words related to recovery and recycling

    oai_token-act-pair · gpt-3.5-turbo

    words related to recycling or reuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.76
    yip
    -0.76
    inki
    -0.63
    ovych
    -0.61
     acqu
    -0.61
    recomm
    -0.61
     hypers
    -0.59
     Lords
    -0.58
    anamo
    -0.57
    awan
    -0.56
    POSITIVE LOGITS
    cled
    0.98
    ascript
    0.82
    rocal
    0.81
    entials
    0.80
    tions
    0.80
    stantial
    0.76
    brance
    0.76
    lator
    0.76
    urate
    0.75
    ctive
    0.74
    Act Density 0.071%

    No Known Activations