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

    Neuronpedia

    INDEX
    Explanations

    passive forms of communication where information is shared or exchanged

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I was told" or similar constructions indicating received information or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adesh
    -0.72
    ivot
    -0.71
    Labor
    -0.69
    ADD
    -0.62
    ications
    -0.62
    insula
    -0.61
    odox
    -0.60
     limb
    -0.59
    asu
    -0.59
    aband
    -0.59
    POSITIVE LOGITS
    tale
    0.86
    mith
    0.74
     goodbye
    0.71
     tales
    0.69
     permission
    0.69
    Ń·
    0.68
    ļé
    0.66
     repeatedly
    0.65
    esson
    0.65
    ĨĴ
    0.64
    Act Density 0.031%

    No Known Activations