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

    Neuronpedia

    INDEX
    Explanations

    prepositions particularly focusing on the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Zacks
    -0.68
    ManagedBean
    -0.64
     Jove
    -0.60
    untung
    -0.59
     Pyrene
    -0.58
    EReference
    -0.56
    ful
    -0.56
     Tadeusz
    -0.55
     Mahomet
    -0.54
    sequelize
    -0.54
    POSITIVE LOGITS
     behalf
    1.67
     the
    1.19
     both
    0.81
     a
    0.80
     its
    0.78
    .}(
    0.77
     occasion
    0.76
     their
    0.75
     how
    0.75
    }]$
    0.72
    Act Density 0.335%

    No Known Activations