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

    Neuronpedia

    INDEX
    Explanations

    comparative statements or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    board
    -0.80
    yp
    -0.71
    yth
    -0.69
    ident
    -0.67
    aper
    -0.64
    ortion
    -0.64
    pron
    -0.63
    path
    -0.63
    angel
    -0.62
    iver
    -0.61
    POSITIVE LOGITS
     nor
    0.71
    soever
    0.70
     Brach
    0.69
    £ı
    0.69
    osate
    0.68
    CLE
    0.68
     Clancy
    0.67
    algia
    0.66
    glas
    0.66
     Commando
    0.66
    Act Density 0.153%

    No Known Activations