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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by action words

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "going into" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nell
    -0.67
    friend
    -0.64
    copy
    -0.63
    guyen
    -0.60
    ĺħ
    -0.59
    âĤ¬
    -0.58
    gnu
    -0.58
    bane
    -0.57
    ect
    -0.57
    ice
    -0.57
    POSITIVE LOGITS
    veyard
    0.80
    vernment
    0.79
     hiber
    0.75
     adulthood
    0.74
    qus
    0.74
     trance
    0.71
     earthqu
    0.69
    clusion
    0.69
     rehab
    0.69
    jured
    0.69
    Act Density 0.037%

    No Known Activations