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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.91
     Houſe
    -0.86
     Jefus
    -0.73
     lpg
    -0.72
     cdti
    -0.70
     sandero
    -0.70
     photolibrary
    -0.69
    stdc
    -0.69
     EEU
    -0.68
     يتيمه
    -0.68
    POSITIVE LOGITS
     the
    0.84
     it
    0.80
    the
    0.76
     there
    0.74
     namely
    0.71
     The
    0.71
     hence
    0.71
     they
    0.70
    there
    0.69
     although
    0.68
    Act Density 0.265%

    No Known Activations