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

    Neuronpedia

    INDEX
    Explanations

    terms indicating availability or status updates regarding projects and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initially
    -0.65
     otherwise
    -0.62
     brav
    -0.60
     similarity
    -0.60
    amba
    -0.60
     bells
    -0.60
     blah
    -0.59
     originally
    -0.57
     meantime
    -0.57
     beforehand
    -0.56
    POSITIVE LOGITS
    here
    0.74
     defunct
    0.68
    YL
    0.67
    livion
    0.67
    YP
    0.66
    orthy
    0.66
    aukee
    0.66
    CLUS
    0.66
    Reviewer
    0.65
    Ô
    0.64
    Act Density 0.142%

    No Known Activations