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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrasal verbs indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sails
    -0.64
    kj
    -0.63
     Crown
    -0.61
     Tsukuyomi
    -0.60
     cir
    -0.59
     Matter
    -0.57
     SOFTWARE
    -0.57
     Falling
    -0.57
    ãĥ«
    -0.56
     Runes
    -0.55
    POSITIVE LOGITS
     athlet
    0.86
     withd
    0.85
     financially
    0.79
     economically
    0.76
    ptin
    0.76
     against
    0.75
     blindly
    0.73
    istrate
    0.72
    merce
    0.71
     territ
    0.71
    Act Density 0.326%

    No Known Activations