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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     playbook
    -0.78
    orum
    -0.68
    atti
    -0.67
    rpm
    -0.67
    yo
    -0.66
    Media
    -0.65
     PACs
    -0.64
    éĩ
    -0.63
     Leadership
    -0.63
     archives
    -0.61
    POSITIVE LOGITS
    inarily
    0.85
     largeDownload
    0.81
    ilst
    0.75
     unwelcome
    0.74
    arb
    0.73
    perty
    0.68
    isode
    0.67
    iled
    0.65
    phant
    0.65
     ende
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.