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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial or conceptual boundaries

    oai_token-act-pair · gpt-3.5-turbo

    words related to continuity and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.84
     Wolves
    -0.72
    Pear
    -0.67
     Sunshine
    -0.66
     shed
    -0.66
    BSD
    -0.66
    cffffcc
    -0.64
     Knights
    -0.63
    UGE
    -0.61
     Silicon
    -0.60
    POSITIVE LOGITS
     cont
    1.02
    oso
    0.96
    rast
    0.93
    ented
    0.84
    rived
    0.83
    raints
    0.82
    ours
    0.82
     arrang
    0.81
     toile
    0.80
    itions
    0.80
    Act Density 0.007%

    No Known Activations