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

    Neuronpedia

    INDEX
    Explanations

    relationships and dependencies between various factors or variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     [],
    -0.67
     poffe
    -0.63
    };*/
    -0.57
     raiſ
    -0.57
     leſs
    -0.56
     []),
    -0.55
     prohibido
    -0.54
    noks
    -0.54
     houſe
    -0.54
     típico
    -0.53
    POSITIVE LOGITS
    脚注の使い方
    0.57
     gyhoeddwyd
    0.57
    +:+
    0.56
     nawr
    0.55
    ChildScrollView
    0.53
    
    0.53
    GEBURTSDATUM
    0.52
     protoimpl
    0.51
    Datuak
    0.49
    PreferredItem
    0.49
    Act Density 0.957%

    No Known Activations