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

    Neuronpedia

    INDEX
    Explanations

    events or actions that happened since a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the establishment and development of organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alog
    -0.69
    rouse
    -0.62
    avy
    -0.59
    Production
    -0.59
    Fax
    -0.59
     envy
    -0.57
    jac
    -0.57
    eping
    -0.57
    Ry
    -0.57
     blot
    -0.56
    POSITIVE LOGITS
     Trafford
    0.80
     withd
    0.68
     landfall
    0.65
    verty
    0.63
     Dise
    0.63
     inception
    0.63
     targ
    0.60
     territ
    0.60
     independence
    0.60
     formally
    0.59
    Act Density 0.184%

    No Known Activations