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

    Neuronpedia

    INDEX
    Explanations

    phrases and constructions expressing possibility or speculation

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

    potential outcomes or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.65
     للاسماء
    -0.62
    DIPSETTING
    -0.50
    SequentialGroup
    -0.49
    Портали
    -0.49
    ientras
    -0.47
     smrti
    -0.47
    الدراسه
    -0.47
     AssemblyVersion
    -0.46
    carteles
    -0.46
    POSITIVE LOGITS
     potential
    0.46
     Potential
    0.44
     poten
    0.42
    Potential
    0.41
    microb
    0.41
     став
    0.39
    potential
    0.39
    UNC
    0.39
     cau
    0.38
     future
    0.38
    Act Density 0.026%

    No Known Activations