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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preparation or readiness for an event or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expecting about to happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.32
     UnityEngine
    -0.32
    Mnemonic
    -0.31
    antMatchers
    -0.30
    िख
    -0.30
    *************/
    -0.29
    ».
    -0.28
    ImageContext
    -0.28
     densidad
    -0.28
    dictionary
    -0.27
    POSITIVE LOGITS
     Expect
    0.58
     Walkover
    0.55
    ]")]
    0.55
     besk
    0.55
    お楽しみに
    0.52
     ModelExpression
    0.52
    面倒
    0.52
    icoot
    0.51
     budete
    0.51
     pronti
    0.51
    Act Density 0.081%

    No Known Activations