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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visibility or visual perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astify
    -0.76
    neurial
    -0.63
    revalidate
    -0.63
    NamedQueries
    -0.63
     Lala
    -0.60
    AutoField
    -0.59
    warden
    -0.58
    istoitu
    -0.57
     propOrder
    -0.57
    zzlement
    -0.57
    POSITIVE LOGITS
     vis
    0.90
     Vis
    0.89
    vis
    0.79
    Vis
    0.76
     VIS
    0.69
    VIS
    0.59
     visi
    0.50
     vise
    0.49
     viso
    0.49
     viser
    0.47
    Act Density 0.125%

    No Known Activations