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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing anticipation or expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express anticipation or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elementary
    -0.68
    LOD
    -0.63
    roy
    -0.62
    MENT
    -0.60
     ABE
    -0.60
     Palestin
    -0.57
    MET
    -0.57
    Interstitial
    -0.57
     misdem
    -0.56
    ç«
    -0.55
    POSITIVE LOGITS
     forward
    1.81
    forward
    1.42
     Forward
    1.36
     forwards
    1.29
    Forward
    1.14
    ahead
    1.13
     ahead
    0.98
     backward
    0.94
     Ahead
    0.94
    oward
    0.92
    Act Density 0.039%

    No Known Activations