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

    Neuronpedia

    INDEX
    Explanations

    numeric values indicating quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote a minimum quantity or threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.74
    tions
    -0.72
     Dynamics
    -0.65
    selves
    -0.64
     DRAG
    -0.61
    rend
    -0.60
    ALLY
    -0.59
    bath
    -0.59
    vim
    -0.58
    ãĥ¼ãĤ¯
    -0.58
    POSITIVE LOGITS
    uner
    0.81
    foundland
    0.76
     partially
    0.71
     toler
    0.70
    egal
    0.67
    rador
    0.65
    omething
    0.65
     half
    0.64
     habitable
    0.63
     quarter
    0.63
    Act Density 0.024%

    No Known Activations