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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases that emphasize a point or transition in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaar
    -0.19
    -League
    -0.17
    udeau
    -0.17
    niÄį
    -0.16
    abad
    -0.16
    ungan
    -0.16
     Král
    -0.15
    ruc
    -0.15
    prung
    -0.15
    poons
    -0.14
    POSITIVE LOGITS
     far
    0.21
    -called
    0.20
    iled
    0.20
    ething
    0.18
    iling
    0.18
    far
    0.17
    ber
    0.17
    aking
    0.17
    fter
    0.16
    jaw
    0.16
    Act Density 0.060%

    No Known Activations