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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    historical dates or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecause
    -0.59
    icular
    -0.59
    ²¾
    -0.59
    dfx
    -0.58
    different
    -0.57
    inese
    -0.55
     desserts
    -0.55
    dule
    -0.53
     hungry
    -0.53
     dracon
    -0.53
    POSITIVE LOGITS
    .;
    0.97
    ;;;;;;;;;;;;
    0.82
    Reviewed
    0.80
    };
    0.79
     };
    0.72
    ;
    0.71
     Dear
    0.69
     DOI
    0.69
     âĨij
    0.68
     RELEASE
    0.68
    Act Density 0.349%

    No Known Activations