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

    Neuronpedia

    INDEX
    Explanations

    themes related to experimentation and flexibility in decision-making processes

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

    experimenting to find what you like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ELTS
    -0.51
     kohdetta
    -0.47
    ſehen
    -0.44
    CppMethod
    -0.44
    enterOuterAlt
    -0.44
    omock
    -0.42
    zeh
    -0.42
    sete
    -0.41
     nv
    -0.40
    IRUS
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.50
     experimenting
    0.46
     <>",
    0.43
     experimentation
    0.43
    principalColumn
    0.42
     adjustment
    0.42
    嘗試
    0.41
     adjusting
    0.40
     parha
    0.40
     parseFrom
    0.39
    Act Density 0.236%

    No Known Activations