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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or flow

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and related forms of verbs indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ£
    -0.72
    phies
    -0.71
    ãĥ¼ãĥ³
    -0.68
    ãĥĨ
    -0.68
    ãĥ¯ãĥ³
    -0.68
    byn
    -0.67
    ãĥĸ
    -0.65
    rik
    -0.64
    rification
    -0.63
    rament
    -0.63
    POSITIVE LOGITS
     forth
    0.81
     outward
    0.80
     onto
    0.77
     downwards
    0.77
    ishly
    0.74
     downhill
    0.72
     upward
    0.72
     glow
    0.71
     pear
    0.69
     emanating
    0.69
    Act Density 0.118%

    No Known Activations