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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases indicating specificity or examples within a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.20
    GEBURTSDATUM
    -1.03
     "..\..\..\
    -0.97
    
    -0.87
    tableFuture
    -0.86
     odkazy
    -0.84
    AndEndTag
    -0.84
    contentLoaded
    -0.84
    IVEREF
    -0.84
    ์ตูน
    -0.82
    POSITIVE LOGITS
    Fantas
    0.52
     caus
    0.49
    Ins
    0.48
    Os
    0.48
     IMS
    0.48
    στα
    0.47
    ksjon
    0.47
    Spe
    0.47
    Est
    0.46
    าส
    0.46
    Act Density 0.045%

    No Known Activations