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

    Neuronpedia

    INDEX
    Explanations

    instructions or steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps related to a process or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attRot
    -0.77
    else
    -0.75
     regrets
    -0.73
     consequently
    -0.69
     likewise
    -0.68
    urther
    -0.67
    Others
    -0.67
     latter
    -0.66
    avoid
    -0.66
    Elsewhere
    -0.65
    POSITIVE LOGITS
     randomly
    0.91
     rectangle
    0.77
     outline
    0.77
     cardboard
    0.76
     rectangular
    0.76
     random
    0.74
     predetermined
    0.74
     dataset
    0.72
     folder
    0.71
     sheet
    0.71
    Act Density 0.592%

    No Known Activations