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

    Neuronpedia

    INDEX
    Explanations

    references to irreversible medical conditions or significant health risks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    stris
    -0.56
    egl
    -0.46
    blower
    -0.44
    uksessa
    -0.44
    новременно
    -0.43
    BOURNE
    -0.43
     twister
    -0.42
    schirm
    -0.42
     indirect
    -0.42
     omission
    -0.41
    POSITIVE LOGITS
    yntaxException
    0.73
    GEBURTSDATUM
    0.71
     cherchés
    0.66
     recoverable
    0.64
    AddTagHelper
    0.63
     MainAxisSize
    0.63
     محفوظة
    0.61
     RECOVERY
    0.60
     utafitiHapana
    0.60
    ArrowToggle
    0.59
    Act Density 0.243%

    No Known Activations