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

    Neuronpedia

    INDEX
    Explanations

    phrases related to existence or presence, particularly focusing on the verb "be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Anis
    -0.91
    hdashline
    -0.85
    expandindo
    -0.82
    RegistryLite
    -0.81
    Personendaten
    -0.81
    Olvid
    -0.80
     Isi
    -0.79
     Jefus
    -0.79
     Forman
    -0.79
    PathVariable
    -0.77
    POSITIVE LOGITS
     be
    1.19
    Be
    1.02
     Be
    0.98
    be
    0.96
    ReusableCell
    0.89
     Bevan
    0.73
     Audiodateien
    0.71
     Belich
    0.71
     BE
    0.71
    ={()=>
    0.69
    Act Density 1.319%

    No Known Activations