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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation or absence

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences that contain the word "Nothing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.64
    nikov
    -0.64
    grad
    -0.63
    PsyNetMessage
    -0.62
     Spectrum
    -0.61
    oak
    -0.60
    assis
    -0.60
    orks
    -0.59
    ilt
    -0.59
    CVE
    -0.59
    POSITIVE LOGITS
     else
    1.41
    Else
    1.11
     whatsoever
    1.01
     Else
    0.88
     remotely
    0.83
     happened
    0.80
     resembling
    0.77
     happens
    0.77
     imaginable
    0.77
     bothering
    0.76
    Act Density 0.039%

    No Known Activations