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

    Neuronpedia

    INDEX
    Explanations

    words related to shift or movement

    oai_token-act-pair · gpt-3.5-turbo

    the word "ift" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dod
    -0.70
     known
    -0.65
     penetrating
    -0.63
     Cav
    -0.63
     controlled
    -0.63
     repeated
    -0.61
     Bers
    -0.61
     stud
    -0.61
     seriously
    -0.60
     Ars
    -0.60
    POSITIVE LOGITS
    ift
    4.38
    ifts
    2.47
    IFT
    2.32
    ifted
    2.27
    ifting
    2.10
    ifter
    1.86
    ifty
    1.66
    lift
    1.31
    aunder
    1.02
    shift
    0.99
    Act Density 0.002%

    No Known Activations