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

    Neuronpedia

    INDEX
    Explanations

    suffixes and endings that suggest abstract or conceptual themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    st
    -0.36
    sto
    -0.29
    studio
    -0.24
    sta
    -0.24
    ston
    -0.23
    sti
    -0.23
    sth
    -0.22
    stat
    -0.22
    sten
    -0.22
    story
    -0.22
    POSITIVE LOGITS
    yyyy
    0.35
    yyy
    0.32
    tics
    0.29
    town
    0.28
    esterday
    0.28
    lation
    0.27
    outube
    0.26
    ielding
    0.26
    ields
    0.25
    yy
    0.24
    Act Density 0.997%

    No Known Activations