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

    Neuronpedia

    INDEX
    Explanations

    instances of code or text referencing temporary files or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Angeli
    -0.50
     Ellis
    -0.49
    PENDAHULUAN
    -0.49
     Silber
    -0.48
     succinct
    -0.48
     meaningfully
    -0.48
    loyds
    -0.48
     Chio
    -0.47
     Ried
    -0.47
    对其
    -0.47
    POSITIVE LOGITS
     myſelf
    0.60
     pleaſure
    0.53
     raiſ
    0.48
     houſe
    0.48
     fhew
    0.47
    contact
    0.47
     fubject
    0.47
     poffible
    0.46
     contact
    0.46
     repos
    0.45
    Act Density 0.234%

    No Known Activations