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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to social awkwardness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social discomfort or awkward situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptives
    -0.85
    ptive
    -0.82
    ignty
    -0.79
    ULTS
    -0.71
    idation
    -0.71
    vation
    -0.70
    tsky
    -0.70
    aders
    -0.70
    IVER
    -0.70
    FORE
    -0.69
    POSITIVE LOGITS
    ness
    1.39
    nesses
    1.07
    ly
    0.86
    ety
    0.86
    ity
    0.85
    entimes
    0.80
    itude
    0.77
    NESS
    0.77
     awkward
    0.76
    kward
    0.76
    Act Density 0.025%

    No Known Activations