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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their associated phrases indicating potentiality or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alimentaires
    -0.53
    UserScript
    -0.51
     relazioni
    -0.51
     noce
    -0.51
     surla
    -0.49
    self
    -0.49
     feit
    -0.48
     inoltre
    -0.47
     ICF
    -0.47
    Portale
    -0.47
    POSITIVE LOGITS
    LEncoder
    0.84
    &+
    0.76
    примеча
    0.76
    ‚¬
    0.73
    lidean
    0.72
    āya
    0.72
    sequelize
    0.72
    metz
    0.72
    .)}
    0.71
    dellín
    0.70
    Act Density 0.510%

    No Known Activations