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

    Neuronpedia

    INDEX
    Explanations

    dates and specific historical events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation and conjunctions in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hub
    -0.77
    imeter
    -0.71
    jad
    -0.70
    zens
    -0.68
    arie
    -0.68
    resa
    -0.67
    ":"/
    -0.66
    "]=>
    -0.65
    ":-
    -0.65
    });
    -0.64
    POSITIVE LOGITS
     culminating
    1.36
     resulting
    1.29
     thereby
    1.19
     causing
    1.16
     intending
    1.15
     whilst
    1.12
     wherein
    1.10
     allowing
    1.10
     whence
    1.08
     concluding
    1.05
    Act Density 0.304%

    No Known Activations