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

    Neuronpedia

    INDEX
    Explanations

    instances where actions like 'send' are directed at the reader

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sending messages or emails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.73
    urity
    -0.71
    heid
    -0.70
    orsi
    -0.67
    jamin
    -0.63
    profit
    -0.60
    OWER
    -0.60
    doms
    -0.60
    rehens
    -0.60
     Fas
    -0.59
    POSITIVE LOGITS
    iments
    0.83
    mail
    0.83
     invitations
    0.82
    inel
    0.82
    keys
    0.81
     SMS
    0.80
    Mail
    0.80
    ãĥĥãĥī
    0.79
    imental
    0.79
     messages
    0.78
    Act Density 0.025%

    No Known Activations