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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.65
    è¦ļéĨĴ
    -0.62
     dod
    -0.62
    VERTISEMENT
    -0.60
     oust
    -0.59
     litter
    -0.58
    itent
    -0.58
     nun
    -0.58
     eh
    -0.58
     belly
    -0.56
    POSITIVE LOGITS
    gotten
    1.39
    bidden
    1.37
    theless
    1.13
    gettable
    1.08
    giving
    0.99
    wards
    0.97
    rontal
    0.97
    give
    0.96
    getting
    0.96
    etheless
    0.94
    Act Density 0.015%

    No Known Activations