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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to storytelling or movie plots

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soType
    -0.93
    gio
    -0.93
     misses
    -0.83
    catentry
    -0.81
    orth
    -0.78
    inventoryQuantity
    -0.77
    enthal
    -0.77
    endif
    -0.77
     endif
    -0.77
     forgetting
    -0.76
    POSITIVE LOGITS
     Discover
    0.82
     premise
    0.81
     essentially
    0.79
     Essentially
    0.77
     simple
    0.77
     loosely
    0.76
     ingenious
    0.76
    ezvous
    0.75
     Participants
    0.75
    ablished
    0.74
    Act Density 5.936%

    No Known Activations