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

    Neuronpedia

    INDEX
    Explanations

    phrases related to asking for feedback or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a desire for feedback or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ths
    -0.64
     pse
    -0.64
    ABC
    -0.62
    requires
    -0.58
     transpired
    -0.58
    Loc
    -0.57
     Simply
    -0.57
    phe
    -0.57
    soever
    -0.57
     Laf
    -0.57
    POSITIVE LOGITS
    uate
    0.79
    CLASSIFIED
    0.73
    uctions
    0.69
     someday
    0.66
     emulate
    0.66
     disruptive
    0.65
    anything
    0.65
    gress
    0.64
     FANTASY
    0.62
    ayne
    0.61
    Act Density 0.268%

    No Known Activations