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

    Neuronpedia

    INDEX
    Explanations

    phrases related to small versions or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    references to "mini" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âķIJâķIJ
    -0.78
    Ö¼
    -0.76
    xual
    -0.71
    IAL
    -0.65
    REAM
    -0.64
    lain
    -0.63
     defe
    -0.62
    mingham
    -0.60
    metic
    -0.60
    fully
    -0.60
    POSITIVE LOGITS
    ature
    1.55
    atur
    1.35
    atures
    1.18
    ota
    0.86
     sized
    0.83
    istered
    0.79
    eco
    0.79
    ocular
    0.79
    ogo
    0.74
    oby
    0.73
    Act Density 0.024%

    No Known Activations