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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future expectations and projections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.60
    存于互联网档案馆
    -0.56
     dall
    -0.51
    MarshalTo
    -0.51
    rovna
    -0.49
    :@"
    -0.49
    Saying
    -0.47
    世的
    -0.47
    世
    -0.47
    Einzelnachweise
    -0.47
    POSITIVE LOGITS
     likely
    1.08
     Likely
    0.98
    likely
    0.94
    Likely
    0.93
     slated
    0.87
     expected
    0.87
     unlikely
    0.84
     deverá
    0.83
     vora
    0.83
     waarschijnlijk
    0.82
    Act Density 0.224%

    No Known Activations