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

    Neuronpedia

    INDEX
    Explanations

    references to control or manipulation within interpersonal dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     étrangère
    -0.72
     stället
    -0.71
     étoit
    -0.64
     pouvoit
    -0.61
     auroit
    -0.60
     sauvage
    -0.57
     magique
    -0.56
     Anſ
    -0.56
     répon
    -0.56
     sauvages
    -0.56
    POSITIVE LOGITS
    raad
    0.55
    LogFactory
    0.55
    jsoup
    0.53
    ngdoc
    0.53
    endpush
    0.52
     CreateTagHelper
    0.51
    endphp
    0.51
    awtextra
    0.51
    ArgsConstructor
    0.49
    GEBURTSDATUM
    0.49
    Act Density 0.120%

    No Known Activations