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

    Neuronpedia

    INDEX
    Explanations

    numerical values and financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    favor
    -0.72
    neighborhood
    -0.71
     FAVOR
    -0.69
    Honorable
    -0.67
     rumor
    -0.66
     favor
    -0.66
     theater
    -0.66
     neighborhood
    -0.64
     rumors
    -0.63
    favorable
    -0.62
    POSITIVE LOGITS
     programme
    0.70
     £
    0.61
     (£
    0.58
    pm
    0.57
     programmes
    0.57
    am
    0.56
    HasOne
    0.56
     PROGRAMME
    0.55
     Programme
    0.55
     ţ
    0.53
    Act Density 0.135%

    No Known Activations