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

    Neuronpedia

    INDEX
    Explanations

    phrases describing collaborative efforts or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    commas used in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arah
    -0.66
     |--
    -0.62
    nai
    -0.62
     recognise
    -0.58
     taxing
    -0.57
    estinal
    -0.57
     ident
    -0.55
    rolet
    -0.55
    gently
    -0.55
    heartedly
    -0.55
    POSITIVE LOGITS
     whom
    0.92
     whose
    0.88
     who
    0.79
     pandemonium
    0.78
     there
    0.76
     Inc
    0.72
     we
    0.71
     Jr
    0.68
    who
    0.67
    there
    0.67
    Act Density 0.200%

    No Known Activations