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

    Neuronpedia

    INDEX
    Explanations

    suggestions or examples for trying something new

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ſelf
    -0.96
     myſelf
    -0.95
     itſelf
    -0.93
     ſy
    -0.92
     ſche
    -0.90
    PrototypeOf
    -0.90
     ―――――
    -0.89
     houſe
    -0.89
     Monfieur
    -0.89
     themſelves
    -0.88
    POSITIVE LOGITS
     Ly
    0.48
     fi
    0.47
     an
    0.46
     N
    0.45
     indul
    0.43
     Rukh
    0.43
     S
    0.42
    ymce
    0.42
    DotNetBar
    0.40
    solete
    0.40
    Act Density 0.040%

    No Known Activations