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

    Neuronpedia

    INDEX
    Explanations

    contact information and ways to reach people

    oai_token-act-pair · gpt-3.5-turbo

    instances of contact information or reachability details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roman
    -0.72
     subp
    -0.69
    knife
    -0.68
    ajo
    -0.67
    alon
    -0.64
    matter
    -0.64
     cannibal
    -0.63
    gone
    -0.63
     limb
    -0.62
    cott
    -0.61
    POSITIVE LOGITS
     Toll
    0.72
    ---------
    0.72
    Contact
    0.70
     {*
    0.69
    ioned
    0.69
    Tel
    0.68
     via
    0.66
     Send
    0.66
    tel
    0.66
    Attempts
    0.65
    Act Density 0.047%

    No Known Activations