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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating past actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.64
    gatsby
    -0.63
    각주
    -0.59
     varandra
    -0.59
     CURIAM
    -0.57
    PYX
    -0.56
    Erreferentziak
    -0.54
     travaillons
    -0.53
     zijne
    -0.53
    jspx
    -0.53
    POSITIVE LOGITS
    Whilst
    0.85
     Whilst
    0.79
     whilst
    0.76
    initialise
    0.74
     recognised
    0.74
     specialises
    0.72
     classed
    0.67
     specialise
    0.65
     recognises
    0.64
     specialist
    0.64
    Act Density 0.229%

    No Known Activations