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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific discoveries and empirical observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rather
    -0.59
    $.
    -0.56
    burning
    -0.52
     eternity
    -0.51
    ghazi
    -0.51
     rather
    -0.50
    pron
    -0.50
     doorstep
    -0.49
    Tube
    -0.49
     halftime
    -0.48
    POSITIVE LOGITS
     meanwhile
    0.71
     however
    0.64
     sprang
    0.64
     consists
    0.63
     survives
    0.62
     refers
    0.62
     extends
    0.62
     awaits
    0.61
     consisted
    0.60
     translates
    0.59
    Act Density 1.308%

    No Known Activations