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

    Neuronpedia

    INDEX
    Explanations

    terms related to avoidance or evasion

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

    avoiding negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лтамалар
    -0.73
    ImageContext
    -0.69
     Infórmanos
    -0.66
    seamnă
    -0.66
     argint
    -0.61
    таратура
    -0.58
     Chwiliwch
    -0.57
    sidemargin
    -0.57
     transfieras
    -0.57
    ISupport
    -0.57
    POSITIVE LOGITS
     avoidance
    1.40
     avoided
    1.36
    avoid
    1.31
     avoiding
    1.29
     avoid
    1.29
    Avoiding
    1.27
     AVOID
    1.26
     Avoidance
    1.26
    Avoid
    1.23
     avoids
    1.23
    Act Density 0.030%

    No Known Activations