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

    Neuronpedia

    INDEX
    Explanations

    phrases that express frequency or the number of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VEGF
    -0.66
     Demir
    -0.66
     Valladolid
    -0.65
     asl
    -0.65
     Reiki
    -0.64
     Kilkenny
    -0.64
     setae
    -0.64
     Huerta
    -0.63
    Torino
    -0.63
    Unmanaged
    -0.63
    POSITIVE LOGITS
    times
    0.92
     TIMES
    0.89
    TIMES
    0.83
     Times
    0.82
     times
    0.81
    Times
    0.78
    rox
    0.73
    GETHER
    0.73
    0.73
    Extinguishing
    0.71
    Act Density 0.096%

    No Known Activations