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

    Neuronpedia

    INDEX
    Explanations

    sentences that begin with the word "Sure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERS
    -0.18
    sWith
    -0.17
    ers
    -0.16
    ses
    -0.16
    robe
    -0.16
    oggler
    -0.15
    olls
    -0.15
    sim
    -0.15
    orph
    -0.15
    omm
    -0.15
    POSITIVE LOGITS
    fire
    0.47
    -fire
    0.42
    ty
    0.38
    foot
    0.37
    -foot
    0.34
    nder
    0.32
    ties
    0.29
    Fire
    0.28
    -shot
    0.28
    st
    0.28
    Act Density 0.030%

    No Known Activations