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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and explanations in medical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsInitialized
    -0.70
    eker
    -0.50
    łec
    -0.50
     jScrollPane
    -0.50
    PLIES
    -0.49
    intermediate
    -0.48
     hård
    -0.48
    Intermediate
    -0.47
    ciorys
    -0.47
     Administrativna
    -0.46
    POSITIVE LOGITS
     why
    1.04
    why
    0.85
     reasons
    0.84
     reason
    0.80
     mengapa
    0.79
     razão
    0.78
     warum
    0.78
     razón
    0.77
    Reasons
    0.75
    Why
    0.73
    Act Density 0.494%

    No Known Activations