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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the concept of starting over or building anew

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    landa
    -0.17
    lesh
    -0.16
    loff
    -0.15
    arme
    -0.15
    789
    -0.15
    insky
    -0.15
    agi
    -0.14
    ested
    -0.14
    ocket
    -0.14
    çĭ
    -0.14
    POSITIVE LOGITS
     scratch
    0.60
    scratch
    0.46
     Scratch
    0.43
    _scr
    0.39
    Scr
    0.36
     scratched
    0.34
     SCR
    0.34
     scratches
    0.33
     square
    0.33
    cratch
    0.32
    Act Density 0.030%

    No Known Activations