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

    Neuronpedia

    INDEX
    Explanations

    conditional or hypothetical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exerc
    -0.71
    folios
    -0.67
    addon
    -0.63
    english
    -0.63
    osponsors
    -0.62
    inventory
    -0.62
    pillar
    -0.61
    heartedly
    -0.61
    installed
    -0.60
    door
    -0.59
    POSITIVE LOGITS
     prove
    0.81
     provoke
    0.80
     involve
    0.76
     mean
    0.73
     yield
    0.73
     Mean
    0.71
    ニ
    0.70
     introduce
    0.69
     cost
    0.67
     simplify
    0.66
    Act Density 0.145%

    No Known Activations