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

    Neuronpedia

    INDEX
    Explanations

    locations/people's names along with the preposition "from"

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the origin or background of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.85
    faced
    -0.83
    few
    -0.76
    needed
    -0.73
    phabet
    -0.73
    seek
    -0.72
    ilion
    -0.72
    ilation
    -0.70
    ifling
    -0.69
    lethal
    -0.68
    POSITIVE LOGITS
     afar
    1.18
     whence
    0.99
     abroad
    0.90
     Uni
    0.85
     Alexandria
    0.84
     Concord
    0.83
     Guatemala
    0.83
     Tacoma
    0.82
     Ethiopia
    0.82
     Lebanon
    0.81
    Act Density 0.120%

    No Known Activations