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

    Neuronpedia

    INDEX
    Explanations

    communication methods and platforms, such as social media and phone calls

    oai_token-act-pair · gpt-3.5-turbo

    elements related to social media interactions and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.72
     Appears
    -0.62
    massive
    -0.60
    ammy
    -0.58
    abama
    -0.58
    hap
    -0.57
    ahime
    -0.57
    civil
    -0.56
    iage
    -0.54
    merce
    -0.54
    POSITIVE LOGITS
     beforehand
    0.64
    DIT
    0.56
     memor
    0.53
     memos
    0.52
     factual
    0.52
     {*
    0.51
    ascript
    0.50
     cues
    0.49
     aloud
    0.49
     omission
    0.49
    Act Density 1.996%

    No Known Activations