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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement and location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its contextual relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivia
    -0.79
    ãĥīãĥ©
    -0.75
    etically
    -0.74
    atural
    -0.73
    ebted
    -0.70
    proven
    -0.68
    adden
    -0.68
    plete
    -0.67
    IPP
    -0.67
    eday
    -0.66
    POSITIVE LOGITS
     doorway
    1.43
     hallway
    1.36
     courtyard
    1.31
     room
    1.30
     balcony
    1.28
     door
    1.26
     porch
    1.24
     apartment
    1.23
     bedroom
    1.22
     bathroom
    1.20
    Act Density 0.163%

    No Known Activations