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

    Neuronpedia

    INDEX
    Explanations

    paragraphs with detailed descriptions and technical information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to analysis and inference processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.73
    `.
    -0.71
     Advertisement
    -0.68
    Medium
    -0.66
    %.
    -0.65
    $.
    -0.64
    thia
    -0.64
    >.
    -0.64
    }.
    -0.63
    ''.
    -0.63
    POSITIVE LOGITS
     politically
    0.55
     domestically
    0.54
     sequ
    0.53
     locally
    0.53
     physically
    0.52
     rehearsal
    0.52
     technically
    0.52
     exhaustive
    0.51
    oslav
    0.51
     constraints
    0.50
    Act Density 1.945%

    No Known Activations