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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the location or movement of objects

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns that indicate ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vine
    -0.65
    itect
    -0.62
     disposed
    -0.62
    cephal
    -0.60
    aways
    -0.60
     Russ
    -0.58
    antine
    -0.58
     alike
    -0.57
    GAN
    -0.57
    ocument
    -0.57
    POSITIVE LOGITS
     own
    1.12
     footing
    1.06
     rightful
    0.98
     fair
    0.93
     destiny
    0.92
     stride
    0.91
     bearings
    0.86
     quota
    0.83
     groove
    0.80
     tremend
    0.80
    Act Density 0.133%

    No Known Activations