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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases starting with "into"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "went into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.68
    friend
    -0.67
    friends
    -0.64
    gemony
    -0.64
    gnu
    -0.63
    CHA
    -0.61
     Ahead
    -0.59
    CTV
    -0.59
    âĤ¬
    -0.58
    footed
    -0.58
    POSITIVE LOGITS
     hiber
    0.90
    qus
    0.81
     trance
    0.80
     detail
    0.80
    veyard
    0.79
    clusion
    0.78
     hiding
    0.78
     cardiac
    0.77
    vernment
    0.77
     bankruptcy
    0.74
    Act Density 0.052%

    No Known Activations