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

    Neuronpedia

    INDEX
    Explanations

    instances of transitional phrases or verbs indicating movement towards various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     both
    -0.18
    both
    -0.15
    -END
    -0.14
     everything
    -0.14
    urovision
    -0.13
    \Url
    -0.13
    neas
    -0.13
    215
    -0.13
    stp
    -0.13
    umbnail
    -0.13
    POSITIVE LOGITS
     gre
    0.21
    æĸ°çļĦ
    0.20
     becomes
    0.19
     new
    0.19
     become
    0.18
     became
    0.18
     being
    0.18
     becoming
    0.17
     embrace
    0.17
     Became
    0.17
    Act Density 0.143%

    No Known Activations