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

    Neuronpedia

    INDEX
    Explanations

    words related to causing a strong emotional or physical reaction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement or action involving waves and shifts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mods
    -0.72
    arel
    -0.61
     guiName
    -0.60
    amy
    -0.57
    umes
    -0.57
    Support
    -0.56
    iru
    -0.55
    ãĤ¤
    -0.54
    ighting
    -0.54
    ume
    -0.53
    POSITIVE LOGITS
     through
    1.65
     thru
    1.46
     Through
    1.24
    through
    1.17
    Through
    1.10
    ochet
    0.95
     trough
    0.95
     past
    0.86
    past
    0.82
     THR
    0.80
    Act Density 0.274%

    No Known Activations