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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of impactful communication and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vice
    -0.16
     Glas
    -0.15
    angan
    -0.14
    erea
    -0.14
    Platforms
    -0.14
    tit
    -0.14
    utches
    -0.14
    iano
    -0.14
    erer
    -0.14
     æ¬
    -0.13
    POSITIVE LOGITS
    zug
    0.15
    eza
    0.15
    że
    0.14
     extrav
    0.14
     ETA
    0.14
    ETA
    0.14
    idable
    0.14
    EP
    0.14
    ziehung
    0.14
    emm
    0.14
    Act Density 0.204%

    No Known Activations