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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial dimensions and layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NgModule
    -0.66
    ñoz
    -0.64
    Források
    -0.63
     GenerationType
    -0.62
    "]));
    -0.61
     уголов
    -0.60
    ม้
    -0.59
    Anmerkungen
    -0.58
    oneofs
    -0.58
    isSuccessful
    -0.57
    POSITIVE LOGITS
    space
    0.79
    spaces
    0.74
    +#+#
    0.67
     houſe
    0.66
    ώς
    0.65
     Acqua
    0.64
    plane
    0.63
     bè
    0.63
    SPACE
    0.61
    pace
    0.61
    Act Density 0.205%

    No Known Activations