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

    Neuronpedia

    INDEX
    Explanations

    terms related to the feasibility of studies or interventions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Mord
    -0.61
     mord
    -0.61
     Bundy
    -0.60
    mord
    -0.58
    Mord
    -0.58
    AGG
    -0.54
    qq
    -0.53
    elsen
    -0.53
     PUN
    -0.52
    SError
    -0.51
    POSITIVE LOGITS
    asibility
    1.32
     Feasibility
    1.27
     feasibility
    1.24
     feasible
    0.92
    asible
    0.92
    \{\\
    0.90
     feas
    0.88
     lenker
    0.84
    ⓘ
    0.84
     kasarigan
    0.78
    Act Density 0.006%

    No Known Activations