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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a contrast or a challenge to a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "though" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.79
    lees
    -0.68
     GEAR
    -0.67
    isible
    -0.67
    enture
    -0.67
    isable
    -0.63
     cryst
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
     nexus
    -0.58
     fundament
    -0.58
    POSITIVE LOGITS
    ts
    1.34
    tons
    1.26
    tern
    0.87
     admittedly
    0.83
    tery
    0.82
    ton
    0.82
    terness
    0.81
    chery
    0.78
    clair
    0.76
    ial
    0.75
    Act Density 0.029%

    No Known Activations