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

    Neuronpedia

    INDEX
    Explanations

    words related to cutting or dividing

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "see"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    initely
    -0.75
    enhagen
    -0.71
    £ı
    -0.71
    INGTON
    -0.70
     hoops
    -0.69
    etheless
    -0.68
    SHIP
    -0.67
    ashtra
    -0.66
    hyde
    -0.62
    è¦ļéĨĴ
    -0.62
    POSITIVE LOGITS
    eps
    1.10
    perate
    1.08
    clusion
    0.98
    vel
    0.96
    vent
    0.95
    eker
    0.95
    ve
    0.94
    xt
    0.94
    pt
    0.93
    rend
    0.92
    Act Density 0.015%

    No Known Activations