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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ResumeLayout
    -0.72
    illères
    -0.63
    ukone
    -0.63
    zerland
    -0.60
    ścic
    -0.60
    Portail
    -0.59
     rentrée
    -0.58
    alate
    -0.57
    rsiniz
    -0.56
    DebuggerNonUser
    -0.56
    POSITIVE LOGITS
    山市
    0.51
    Gemeinden
    0.50
    setopt
    0.49
    WithIOException
    0.46
     Königs
    0.46
    RegistryLite
    0.44
    djangoproject
    0.44
    UnsafeEnabled
    0.43
     orina
    0.43
    reportWebVitals
    0.41
    Act Density 0.094%

    No Known Activations