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

    Neuronpedia

    INDEX
    Explanations

    the name "Keven" and its variant spellings

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ke" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.82
    ashtra
    -0.78
    schild
    -0.75
    åħī
    -0.72
    70710
    -0.71
    é¾įå¥ij士
    -0.68
    IONS
    -0.68
     eleph
    -0.67
    raints
    -0.65
     shelling
    -0.65
    POSITIVE LOGITS
    ptic
    1.03
    SPA
    1.01
    eling
    0.99
    bye
    0.99
    ck
    0.98
    pler
    0.96
    cker
    0.95
    lder
    0.94
    lev
    0.94
    isha
    0.93
    Act Density 0.014%

    No Known Activations