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

    Neuronpedia

    INDEX
    Explanations

    words related to attachments or being attached to something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.74
    mberg
    -0.69
    Ö¼
    -0.65
    Cola
    -0.63
    enthal
    -0.62
    icist
    -0.61
    bane
    -0.61
    ghai
    -0.61
    stall
    -0.61
    asley
    -0.61
    POSITIVE LOGITS
     thereto
    1.25
    ments
    0.91
     securely
    0.79
     attached
    0.79
    ment
    0.74
    ions
    0.73
     attach
    0.73
     Thumbnails
    0.72
     cord
    0.72
    rin
    0.71
    Act Density 0.038%

    No Known Activations