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

    Neuronpedia

    INDEX
    Explanations

    names of a specific company followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AT&T"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.76
    milo
    -0.75
     lin
    -0.75
     inspir
    -0.70
     lessons
    -0.67
     powd
    -0.65
     Laos
    -0.64
    dyl
    -0.63
     caffe
    -0.63
    Reviewer
    -0.63
    POSITIVE LOGITS
    ECH
    0.99
    WA
    0.94
    ruck
    0.89
    OWN
    0.86
    oday
    0.84
    ributes
    0.84
    UNE
    0.83
    CHA
    0.83
    ronics
    0.82
     Mobility
    0.82
    Act Density 0.010%

    No Known Activations