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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to stability and consistency

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "stead" indicating stability or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "$:/
    -0.69
     search
    -0.67
    PLA
    -0.66
     cas
    -0.63
    ACTED
    -0.63
     seeker
    -0.63
     bankruptcy
    -0.60
    tnc
    -0.60
     LCS
    -0.59
    NRS
    -0.59
    POSITIVE LOGITS
    stead
    1.45
    eenth
    0.86
    ijk
    0.84
    ooth
    0.84
    wer
    0.84
    rait
    0.83
    robe
    0.83
    obar
    0.79
    arth
    0.78
    tone
    0.78
    Act Density 0.011%

    No Known Activations