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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.18
    oretical
    -0.16
    arium
    -0.16
     spite
    -0.15
    oret
    -0.15
    soever
    -0.15
    kud
    -0.15
    FTER
    -0.15
    orem
    -0.15
    theless
    -0.15
    POSITIVE LOGITS
     order
    0.21
     hopes
    0.20
    aus
    0.20
    shore
    0.18
    ital
    0.16
     cre
    0.16
     areas
    0.16
    iqu
    0.16
    ns
    0.16
    trans
    0.16
    Act Density 1.307%

    No Known Activations