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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the method or manner in which actions are carried out

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.68
    icio
    -0.67
    ua
    -0.66
     bearer
    -0.66
    inently
    -0.65
    usters
    -0.64
    alty
    -0.64
     livest
    -0.64
    igh
    -0.63
    inately
    -0.63
    POSITIVE LOGITS
     shape
    0.85
    ward
    0.70
    ÙĨ
    0.67
     reminiscent
    0.65
     Sabha
    0.65
    fare
    0.65
    finding
    0.65
    NE
    0.65
     Brach
    0.64
    ãĥĩ
    0.64
    Act Density 0.054%

    No Known Activations