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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements and phrases that relate to assistance or helping others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vron
    -0.17
    ichert
    -0.16
    tons
    -0.15
    TES
    -0.15
    alto
    -0.15
    busters
    -0.15
    quam
    -0.14
    онаÑħ
    -0.14
    ADX
    -0.14
    eut
    -0.14
    POSITIVE LOGITS
     Morrow
    0.17
    èįĴ
    0.17
    egas
    0.16
    992
    0.15
     frank
    0.15
    orsch
    0.14
    iesz
    0.14
    ctor
    0.14
     dev
    0.13
     explo
    0.13
    Act Density 0.004%

    No Known Activations