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

    Neuronpedia

    INDEX
    Explanations

    words related to compound actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compounding or combining various elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borough
    -0.70
    FORE
    -0.70
     Paradise
    -0.63
     Rabbit
    -0.63
     Tale
    -0.61
     Roof
    -0.60
     Pew
    -0.59
     Millennium
    -0.59
     whites
    -0.59
     Greenwich
    -0.59
    POSITIVE LOGITS
    endium
    1.62
    ulsive
    1.40
    artments
    1.35
    ounding
    1.32
    ilers
    1.26
    Lex
    1.24
    ressive
    1.18
    ressing
    1.17
    rehens
    1.15
    assion
    1.14
    Act Density 0.028%

    No Known Activations