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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss existence or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -1.00
    afia
    -0.75
    fect
    -0.72
    ividual
    -0.70
    umbnails
    -0.69
    udeb
    -0.67
    elve
    -0.66
     hail
    -0.66
    onder
    -0.66
    andy
    -0.65
    POSITIVE LOGITS
     happening
    1.21
     untrue
    0.94
     happen
    0.89
     occurring
    0.89
     true
    0.89
    true
    0.86
     TRUE
    0.84
     happened
    0.82
     achievable
    0.80
     accomplished
    0.79
    Act Density 0.152%

    No Known Activations