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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or negation of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     towed
    -0.65
    rex
    -0.64
     crowned
    -0.61
     tossed
    -0.61
     flung
    -0.61
     sped
    -0.58
     raided
    -0.58
    aleb
    -0.58
     prone
    -0.57
    ean
    -0.57
    POSITIVE LOGITS
    xious
    1.17
    except
    0.94
     discern
    0.89
     avail
    0.87
     earthly
    0.86
    oses
    0.86
     meaningful
    0.86
     harm
    0.84
     doubt
    0.84
    ct
    0.84
    Act Density 0.045%

    No Known Activations