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

    Neuronpedia

    INDEX
    Explanations

    words related to extraction and separation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "ext" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.74
    ghai
    -0.72
    pins
    -0.71
    ãĤ´ãĥ³
    -0.69
    Companies
    -0.69
    ãĤ°
    -0.68
     Archdemon
    -0.67
    quartered
    -0.67
    Cola
    -0.67
     Hearts
    -0.66
    POSITIVE LOGITS
    itud
    1.01
     ext
    0.95
    ensional
    0.89
    ensible
    0.88
    ingu
    0.86
    ENDED
    0.84
    ensions
    0.82
    ended
    0.81
    entric
    0.81
    ricular
    0.81
    Act Density 0.004%

    No Known Activations