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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skepticism or doubt

    oai_token-act-pair · gpt-3.5-turbo

    negations expressed in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mechdragon
    -0.69
     PU
    -0.64
    croft
    -0.62
    ochond
    -0.62
     Butt
    -0.62
    owan
    -0.61
     Draw
    -0.61
    dress
    -0.60
     Relationship
    -0.60
     Species
    -0.59
    POSITIVE LOGITS
    't
    1.25
    iting
    0.84
    etsk
    0.84
    ited
    0.82
    nel
    0.79
    tyard
    0.79
    geon
    0.79
    ajor
    0.77
    ates
    0.76
    ounced
    0.75
    Act Density 0.057%

    No Known Activations