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

    Neuronpedia

    INDEX
    Explanations

    statements about scientific theories and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansa
    -0.14
    anship
    -0.14
    ratulations
    -0.14
    ToFit
    -0.14
    renc
    -0.14
    lero
    -0.14
    allen
    -0.14
    ellij
    -0.13
    uchos
    -0.13
    ertest
    -0.13
    POSITIVE LOGITS
    ARGIN
    0.15
    ä¸ĬäºĨ
    0.15
     æ¬
    0.15
    ohan
    0.14
    ONTAL
    0.14
    .synthetic
    0.14
    erot
    0.14
     Joint
    0.14
    acies
    0.14
     Verfügung
    0.13
    Act Density 0.529%

    No Known Activations