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

    Neuronpedia

    INDEX
    Explanations

    fragmented sentences with the word "with" in them, as well as mentions of the word "acrostic"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    facing
    -0.57
     seduce
    -0.54
     facing
    -0.53
     NgModule
    -0.52
    Witam
    -0.52
    MessageType
    -0.52
     approaching
    -0.51
     Facing
    -0.50
     saites
    -0.50
    Rüyada
    -0.49
    POSITIVE LOGITS
    icot
    0.59
     Administrativna
    0.58
    ative
    0.58
    RenderAtEndOf
    0.57
    addCriterion
    0.57
    tdown
    0.53
    SharedCtor
    0.53
    eraus
    0.53
    autant
    0.52
    nthetic
    0.52
    Act Density 1.256%

    No Known Activations