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

    Neuronpedia

    INDEX
    Explanations

    verbs related to bending or warping

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of bending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Countdown
    -0.72
    isation
    -0.71
    oaded
    -0.71
    MSN
    -0.67
    ALE
    -0.65
    istics
    -0.65
    administ
    -0.65
    CHAT
    -0.64
    DN
    -0.64
    employed
    -0.64
    POSITIVE LOGITS
     bends
    1.17
     bend
    1.16
     bending
    0.98
    ĸļ
    0.86
     bent
    0.84
     knees
    0.84
    bent
    0.84
     shack
    0.82
    ¿½
    0.80
     wig
    0.80
    Act Density 0.010%

    No Known Activations