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

    Neuronpedia

    INDEX
    Explanations

    organizations or entities performing actions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "has" indicating possession or action in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reading
    -0.66
    FW
    -0.63
    FL
    -0.63
    ace
    -0.62
    Interested
    -0.61
    ogue
    -0.60
    ttp
    -0.60
    icking
    -0.59
     IMAGES
    -0.59
    matter
    -0.58
    POSITIVE LOGITS
     been
    1.34
     undergone
    1.26
     begun
    1.19
     become
    1.13
     struggled
    1.11
     ceased
    1.07
     gotten
    1.07
     partnered
    1.06
     amassed
    1.01
     fielded
    0.99
    Act Density 0.243%

    No Known Activations