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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.15
    hana
    -0.15
    å¸Ī
    -0.15
    /apis
    -0.15
    sein
    -0.15
    ellites
    -0.14
    ê³Ħ
    -0.14
    éģĩ
    -0.14
    ulis
    -0.14
    elic
    -0.13
    POSITIVE LOGITS
    airo
    0.16
    оÑģÑĮ
    0.16
    aire
    0.16
    .follow
    0.16
    ledo
    0.16
    ings
    0.15
    etto
    0.14
    llen
    0.14
    iba
    0.14
    ifest
    0.14
    Act Density 0.022%

    No Known Activations