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

    Neuronpedia

    INDEX
    Explanations

    negative or conditional phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.88
     NgModule
    -0.82
     Савезне
    -0.81
    ponses
    -0.71
    thâu
    -0.71
     TestBed
    -0.70
     parseFrom
    -0.67
    ymce
    -0.66
    WithIOException
    -0.66
    postsleuth
    -0.66
    POSITIVE LOGITS
    isOk
    0.60
     judiciaire
    0.58
     kebaikan
    0.57
     extérieure
    0.51
    aculture
    0.49
     accett
    0.48
     religieux
    0.47
     latar
    0.47
     aparcamiento
    0.47
     estacionamento
    0.47
    Act Density 0.464%

    No Known Activations