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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the future and conditional outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crement
    -0.18
    mp
    -0.16
    904
    -0.14
    cke
    -0.14
     Ry
    -0.14
    ery
    -0.14
     handic
    -0.14
    Ñĥ
    -0.14
    chet
    -0.14
     kar
    -0.14
    POSITIVE LOGITS
     YOUR
    0.18
    ê°ij
    0.16
     your
    0.16
    YOUR
    0.15
    ë²Ķ
    0.15
    IAM
    0.14
    agens
    0.14
    loquent
    0.14
    rowse
    0.14
    amac
    0.14
    Act Density 0.183%

    No Known Activations