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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and their formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lue
    -0.17
    engo
    -0.15
    ologne
    -0.15
    etat
    -0.15
    urahan
    -0.15
    acias
    -0.15
    braco
    -0.14
    tega
    -0.14
    edores
    -0.14
    atre
    -0.14
    POSITIVE LOGITS
    ritch
    0.13
     Verd
    0.13
     wÅĤa
    0.13
    81
    0.13
    emy
    0.13
     HV
    0.13
    242
    0.12
     graduating
    0.12
     UV
    0.12
     (~(
    0.12
    Act Density 0.012%

    No Known Activations