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

    Neuronpedia

    INDEX
    Explanations

    instructions related to applying or using specific products or tools

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps for tasks involving preparation and usage of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emale
    -0.57
    terday
    -0.49
    ensable
    -0.49
     Establishment
    -0.49
     Accessed
    -0.48
     estranged
    -0.47
     thwarted
    -0.47
     Fundamental
    -0.46
     overrun
    -0.44
     Journalism
    -0.43
    POSITIVE LOGITS
     yourself
    0.88
     yourselves
    0.74
     preferably
    0.73
    instead
    0.70
    epad
    0.70
     instead
    0.69
     ASAP
    0.67
     Yourself
    0.64
     manually
    0.63
     :)
    0.58
    Act Density 0.965%

    No Known Activations