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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition into a particular situation or setting

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    copy
    -0.67
    Bey
    -0.64
    etheless
    -0.62
    cdn
    -0.62
    tesy
    -0.61
    ice
    -0.61
    fortunately
    -0.59
    hai
    -0.59
    tch
    -0.58
     indeed
    -0.57
    POSITIVE LOGITS
     adulthood
    0.85
    veyard
    0.75
    âĸijâĸij
    0.69
     puberty
    0.66
     adolescence
    0.66
     Hungary
    0.65
    hift
    0.64
     hypers
    0.63
     fruition
    0.62
    ital
    0.62
    Act Density 0.042%

    No Known Activations