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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to time, including references to periods, durations, and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.57
     grate
    -0.55
    endum
    -0.51
    Äĩ
    -0.51
    rower
    -0.51
     welcomed
    -0.49
     mustache
    -0.48
     Referred
    -0.48
     Mehran
    -0.48
     softened
    -0.48
    POSITIVE LOGITS
    gress
    0.58
    cycles
    0.57
    usterity
    0.57
    impact
    0.56
    clips
    0.55
    omics
    0.54
    dom
    0.54
    arenthood
    0.53
    abs
    0.52
    idelity
    0.52
    Act Density 1.118%

    No Known Activations