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

    Neuronpedia

    INDEX
    Explanations

    words or phrases relating to interfaces or interactions, particularly in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sville
    -0.18
    arness
    -0.16
    spot
    -0.16
    sz
    -0.16
    tdown
    -0.16
    gz
    -0.15
    slot
    -0.15
    eling
    -0.15
    scious
    -0.15
    eliness
    -0.15
    POSITIVE LOGITS
    iors
    0.24
    ests
    0.24
    ieur
    0.23
    pret
    0.21
    esse
    0.21
    continental
    0.20
    rog
    0.20
     al
    0.20
    ested
    0.19
    IOR
    0.19
    Act Density 0.021%

    No Known Activations