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

    Neuronpedia

    INDEX
    Explanations

    language indicating anticipation or expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing anticipation or eagerness for future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.70
    enthal
    -0.65
    BLIC
    -0.63
     Dwarf
    -0.62
     Lack
    -0.61
    inas
    -0.60
     SATA
    -0.59
    insky
    -0.58
    hem
    -0.58
     Hide
    -0.58
    POSITIVE LOGITS
    ï¸
    0.87
     eagerly
    0.82
     nostalg
    0.79
    WARD
    0.79
    wards
    0.74
    expr
    0.70
     happily
    0.69
     someday
    0.68
    !--
    0.67
    ward
    0.67
    Act Density 0.018%

    No Known Activations