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

    Neuronpedia

    INDEX
    Explanations

    phrases related to local experiences and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.89
     Autorisations
    -0.87
     Houſe
    -0.83
     Efq
    -0.82
     houſe
    -0.81
     pngtree
    -0.81
     CWE
    -0.80
     Autorizaciones
    -0.77
     Monfieur
    -0.76
    AutoScaleMode
    -0.76
    POSITIVE LOGITS
    …
    0.85
    ...
    0.75
    ….
    0.66
    …..
    0.62
    ....
    0.58
    ..
    0.58
     appelez
    0.57
    ho
    0.55
    '
    0.55
    ’
    0.55
    Act Density 0.118%

    No Known Activations