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

    Neuronpedia

    INDEX
    Explanations

    references to the head of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "head" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pac
    -0.72
     destro
    -0.70
     resil
    -0.69
    URA
    -0.68
     mell
    -0.68
     Niet
    -0.67
     sol
    -0.65
    URES
    -0.65
     vo
    -0.64
     pse
    -0.63
    POSITIVE LOGITS
    head
    1.40
    quartered
    1.28
    heading
    1.21
    quarters
    1.20
    quarter
    1.05
    heads
    1.05
    butt
    1.04
    phones
    1.02
    headed
    1.02
    canon
    1.01
    Act Density 0.006%

    No Known Activations