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

    Neuronpedia

    INDEX
    Explanations

    words related to tilting or titled positions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "tilting."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hazard
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    éĹĺ
    -0.74
    CRIP
    -0.73
    ãģķ
    -0.73
    ãĥ¬
    -0.71
    ãĥ©ãĥ³
    -0.71
     Apocalypse
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    æ©
    -0.69
    POSITIVE LOGITS
    terness
    1.08
    ting
    1.07
     tilt
    1.00
     til
    0.88
     tilted
    0.86
    unda
    0.76
    til
    0.74
    vind
    0.73
    abouts
    0.72
    estinal
    0.72
    Act Density 0.008%

    No Known Activations