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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to people or entities in sentences

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

    They followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asimismo
    -0.35
     createSlice
    -0.29
     Additionally
    -0.29
    #+#
    -0.29
     گردد
    -0.28
     subsequently
    -0.27
     dicha
    -0.27
    ApiModelProperty
    -0.26
    ↵↵↵
    -0.26
    <em>
    -0.26
    POSITIVE LOGITS
     queſta
    0.88
     ſei
    0.86
     beſte
    0.82
    <unused52>
    0.81
    <unused8>
    0.80
    [@BOS@]
    0.80
    <unused14>
    0.80
    <unused41>
    0.80
    <unused16>
    0.80
    <unused23>
    0.80
    Act Density 0.063%

    No Known Activations