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

    Neuronpedia

    INDEX
    Explanations

    references to humanity and human nature

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ISMS
    -0.49
    Green
    -0.46
    bule
    -0.46
    mord
    -0.45
    venser
    -0.45
    ancial
    -0.44
    DIPSETTING
    -0.44
    натор
    -0.43
    VIAF
    -0.42
    ifndef
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.86
    ########.
    0.77
    InitVars
    0.68
     CreateTagHelper
    0.67
     محفوظة
    0.67
    ंदीखरीदारी
    0.66
    DockStyle
    0.65
    MockBean
    0.65
    expandindo
    0.64
    ankind
    0.63
    Act Density 0.011%

    No Known Activations